RepublicOfKorokke/Qwen3-4B-Thinking-2507-mlx-mxfp4

This model was converted to MLX format from Qwen/Qwen3-4B-Thinking-2507 using mlx-lm version 0.28.2.

Conversion Command

$ uv run mlx_lm.convert --hf-path Qwen/Qwen3-4B-Thinking-2507 --mlx-path Qwen3-4B-Thinking-2507-mlx-mxfp4 -q --q-mode mxfp4 --q-group-size 32

Safetensors

Model size

0.8B params

Tensor type

U32

BF16

Model tree for RepublicOfKorokke/Qwen3-4B-Thinking-2507-mlx-mxfp4

Base model

Quantized

(78)

this model