This model was converted to MLX format from https://huggingface.co/LiquidAI/LFM2-8B-A1B using mlx-lm version 0.30.5.

Conversion Command

$ uv run mlx_lm.convert --hf-path LiquidAI/LFM2-8B-A1B --mlx-path LFM2-8B-A1B-mlx-mxfp4 -q --q-mode nvfp4 --q-group-size 16

Downloads last month
16
Safetensors
Model size
2B params
Tensor type
U8
U32
BF16
F32
MLX
Hardware compatibility
Log In to add your hardware

4-bit

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

Model tree for RepublicOfKorokke/LFM2-8B-A1B-mlx-nvfp4

Quantized
(28)
this model