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
Model size
1.0B params
Tensor type
U8
·
U32 ·
BF16 ·
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for RepublicOfKorokke/Nanbeige4-3B-Thinking-2511-mlx-nvfp4
Base model
Nanbeige/Nanbeige4-3B-Base
Finetuned
Nanbeige/Nanbeige4-3B-Thinking-2511