RepublicOfKorokke/WEBGEN-4B-Preview-mlx-mxfp4

This model was converted to MLX format from Tesslate/WEBGEN-4B-Preview using mlx-lm version 0.28.2.

Conversion Command

$ uv run mlx_lm.convert --hf-path Tesslate/WEBGEN-4B-Preview --mlx-path WEBGEN-4B-Preview-mlx-mxfp4 -q --q-mode mxfp4 --q-group-size 32

Downloads last month
13
Safetensors
Model size
0.8B params
Tensor type
U8
·
U32
·
BF16
·
MLX
Hardware compatibility
Log In to add your hardware

4-bit

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

Model tree for RepublicOfKorokke/WEBGEN-4B-Preview-mlx-mxfp4

Quantized
(10)
this model