This model was converted to MLX format from Nanbeige/Nanbeige4-3B-Thinking-2511 using mlx-lm version 0.30.5.

Conversion Command

$ uv run mlx_lm.convert --hf-path Nanbeige/Nanbeige4-3B-Thinking-2511 --mlx-path Nanbeige4-3B-Thinking-2511-mlx-nvfp4 -q --q-mode nvfp4 --q-group-size 16

Downloads last month
40
Safetensors
Model size
1.0B 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/Nanbeige4-3B-Thinking-2511-mlx-nvfp4

Quantized
(13)
this model