AX-Qwen3.8-Flash-Next-MLX-AXQ-MXFP4-MTP / axquant_quantizer_execution.json
AutomatosX's picture
Publish AX-Qwen3.8-Flash-Next-MLX-AXQ-MXFP4-MTP
ff2a284 verified
Raw History Blame Contribute Delete
191 kB
{
"created_at": "2026-10-04T19:16:32.264697Z",
"plan_sha256": "bc260598c0db87fe643fe31d1936aa03b7f5c2529f2bc8437a32c554f16958c8",
"records": [
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.key_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_0",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_1",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_2",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_3",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_4",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_5",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_6",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_7",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_8",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_9",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_10",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_11",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_12",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_13",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_14",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_15",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_16",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_17",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_18",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_19",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_20",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_21",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_22",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_23",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_24",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_25",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_26",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_27",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_28",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_29",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_30",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_31",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_32",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_33",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_34",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_35",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_36",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_37",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_38",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_39",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_40",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_41",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_42",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_43",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_44",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_45",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_46",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_47",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_48",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_49",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_50",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_51",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_52",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_53",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_54",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_55",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_56",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_57",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_58",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_59",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_60",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_61",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_62",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_63",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_64",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_65",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_66",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_67",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_68",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_69",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_70",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_71",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_72",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_73",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_74",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_75",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_76",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_77",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_78",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_79",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_80",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_81",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_82",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_83",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_84",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_85",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_86",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_87",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_88",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_89",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_90",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_91",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_92",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_93",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_94",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_95",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_96",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_97",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_100",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_101",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_98",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_99",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_102",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_103",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_104",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_105",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_106",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_107",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_108",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_109",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_110",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_111",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_112",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_113",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_114",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_115",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_116",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_117",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_118",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_119",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_120",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_121",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_122",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_123",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_124",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_125",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_126",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_127",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.ple.value_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.self_attn.indexer.index_qk_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.self_attn.indexer.index_qk_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.self_attn.indexer.index_qk_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.self_attn.indexer.index_qk_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.self_attn.indexer.index_qk_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.self_attn.indexer.index_qk_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.30.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.30.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.30.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.30.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.30.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.30.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.30.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.30.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.30.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.30.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.30.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.30.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.31.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.31.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.31.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.31.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.31.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.31.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.31.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.31.self_attn.indexer.index_qk_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.31.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.31.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.31.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.31.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.32.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.32.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.32.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.32.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.32.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.32.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.32.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.32.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.32.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.32.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.32.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.32.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.33.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.33.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.33.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.33.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.33.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.33.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.33.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.33.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.33.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.33.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.33.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.33.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.34.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.34.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.34.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.34.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.34.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.34.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.34.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.34.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.34.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.34.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.34.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.34.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.35.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.35.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.35.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.35.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.35.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.35.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.35.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.35.self_attn.indexer.index_qk_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.35.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.35.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.35.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.35.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.36.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.36.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.36.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.36.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.36.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.36.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.36.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.36.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.36.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.36.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.36.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.36.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.37.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.37.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.37.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.37.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.37.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.37.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.37.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.37.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.37.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.37.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.37.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.37.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.38.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.38.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.38.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.38.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.38.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.38.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.38.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.38.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.38.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.38.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.38.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.38.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.39.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.39.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.39.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.39.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.39.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.39.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.39.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.39.self_attn.indexer.index_qk_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.39.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.39.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.39.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.39.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.40.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.40.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.40.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.40.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.40.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.40.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.40.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.40.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.40.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.40.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.40.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.40.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.41.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.41.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.41.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.41.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.41.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.41.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.41.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.41.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.41.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.41.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.41.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.41.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.42.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.42.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.42.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.42.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.42.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.42.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.42.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.42.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.42.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.42.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.42.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.42.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.43.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.43.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.43.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.43.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.43.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.43.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.43.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.43.self_attn.indexer.index_qk_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.43.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.43.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.43.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.43.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.44.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.44.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.44.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.44.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.44.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.44.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.44.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.44.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.44.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.44.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.44.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.44.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.45.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.45.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.45.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.45.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.45.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.45.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.45.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.45.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.45.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.45.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.45.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.45.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.46.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.46.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.46.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.46.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.46.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.46.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.46.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.46.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.46.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.46.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.46.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.46.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.47.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.47.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.47.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.47.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.47.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.47.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.47.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.47.self_attn.indexer.index_qk_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.47.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.47.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.47.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.47.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.self_attn.indexer.index_qk_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.linear_attn.in_proj_a",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.linear_attn.in_proj_b",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.linear_attn.in_proj_qkv",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.linear_attn.in_proj_z",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.linear_attn.out_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.mlp.experts.gate_up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.embed_tokens",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.mlp.experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.mlp.gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.mlp.shared_expert.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.mlp.shared_expert.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.mlp.shared_expert.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.mlp.shared_expert_gate",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "lm_head",
"note": "mlx-vlm affine packing",
"success": true
}
],
"schema_version": "axquant.quantizer-execution.v2"
}