wenhua cheng

wenhuach's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in Intel/gemma-4-31B-it-int4-AutoRound 7 days ago

Please update chat template

2

#4 opened 7 days ago by

alexcardo

updated a model 7 days ago

Intel/gemma-4-31B-it-int4-AutoRound

6B • Updated 7 days ago • 60.7k • 45

New activity in Intel/gemma-4-31B-it-int4-AutoRound 7 days ago

FP4?

1

#5 opened 7 days ago by

alexcardo

updated a model 7 days ago

Intel/Qwen3.6-35B-A3B-int4-mixed-AutoRound

6B • Updated 7 days ago • 11.3k • 4

published a model 7 days ago

Intel/Qwen3.6-35B-A3B-int4-mixed-AutoRound

6B • Updated 7 days ago • 11.3k • 4

New activity in Intel/Qwen3.6-27B-int4-AutoRound 8 days ago

Why delete Intel/Qwen3.6-35B-A3B-int4-AutoRound?

3

#1 opened 14 days ago by

bgeneto

New activity in Intel/Qwen3.6-27B-int4-AutoRound 9 days ago

does this even run on intel gpus?

3

#2 opened 9 days ago by

Thomas98519864

updated a model 10 days ago

Intel/Qwen3.6-27B-int4-mlx-AutoRound

6B • Updated 10 days ago • 53

published a model 10 days ago

Intel/Qwen3.6-27B-int4-mlx-AutoRound

6B • Updated 10 days ago • 53

updated a model 11 days ago

Intel/Qwen3.6-27B-4.5b-mlx-AutoRound

7B • Updated 11 days ago • 300 • 19

New activity in Intel/Qwen3.6-27B-4.5b-mlx-AutoRound 11 days ago

AutoRound quant fails to load with mlx-lm

👍 1

1

#1 opened 11 days ago by

smcleod

updated a model 11 days ago

Intel/DeepSeek-V4-Flash-W4A16-AutoRound

Text Generation • 40B • Updated 2 days ago • 23.9k • 14

updated a model 14 days ago

Intel/Qwen3.6-27B-int4-AutoRound

6B • Updated 14 days ago • 81k • 26

published 2 models 14 days ago

Intel/Qwen3.6-27B-int4-AutoRound

6B • Updated 14 days ago • 81k • 26

Intel/Qwen3.6-27B-4.5b-mlx-AutoRound

7B • Updated 11 days ago • 300 • 19

updated a model 14 days ago

Intel/Qwen3.5-4B-int4-mlx-AutoRound

1B • Updated 14 days ago • 80 • 1

published a model 14 days ago

Intel/Qwen3.5-4B-int4-mlx-AutoRound

1B • Updated 14 days ago • 80 • 1

liked a model 14 days ago

deepseek-ai/DeepSeek-V4-Pro

Text Generation • 862B • Updated 2 days ago • 1.06M • • 3.74k

New activity in cyankiwi/Qwen3.6-35B-A3B-AWQ-4bit 15 days ago

How does this compare to the original 8bit qwen quant and the 4 bit auto-round quant?

2

#5 opened 20 days ago by

sparx3

New activity in Intel/gemma-4-26B-A4B-it-int4-mixed-AutoRound 16 days ago

any plan for an Ampere compatible version?

2

#2 opened 16 days ago by

electroglyph