matmelis
/

Llama_3.2_1B_w_mxfp4_a_mxfp4_qronos

8-bit precision

Model card Files Files and versions

[INFO] Perplexity: 12.394927024841309

Downloads last month: 3

Safetensors

Model size

0.8B params

Tensor type

BF16

·

U8

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for matmelis/Llama_3.2_1B_w_mxfp4_a_mxfp4_qronos

Base model

meta-llama/Llama-3.2-1B

Quantized

(230)

this model

Collection including matmelis/Llama_3.2_1B_w_mxfp4_a_mxfp4_qronos

Llama-3.2 Qronos

9 items • Updated Aug 20, 2025