Qwen3.5 MLX
Collection
20 items • Updated
This model was converted to MLX format from Qwen/Qwen3.5-0.8B using mlx-vlm version 0.3.12.
Conversion Command
$ uv run mlx_vlm.convert --hf-path Qwen/Qwen3.5-0.8B --mlx-path Qwen3.5-0.8B-mlx-vlm-mxfp4 -q --q-mode mxfp4 --q-group-size 32
uv dependencies
dependencies = ["mlx-lm==0.30.7", "mlx-vlm==0.3.12", "torchvision>=0.25.0"]
- Downloads last month
- 94
Model size
0.2B params
Tensor type
U8
·
U32 ·
BF16 ·
F32 ·
Hardware compatibility
Log In to add your hardware
4-bit