Hugging Peers

NuExtract3-mlx-6bits

☆ Save
by numind mlx
36 downloads 1 likes on Hugging Face updated

Model card

numind/NuExtract3-mlx-6bits

MLX quantized version of numind/NuExtract3.

Quantization

  • mode: affine
  • group_size: 64
  • bits: 6
  • dtype: source/default
  • quant_predicate: none

Usage

pip install -U mlx-vlm
mlx_vlm.generate --model numind/NuExtract3-mlx-6bits --prompt "your prompt"