Hugging Face's logo

numind
/
NuExtract3-mlx-mxfp8

MLX
Safetensors
qwen3_5
mlx-vlm
quantized
8-bit precision
Model card Files
xet
 Community

numind/NuExtract3-mlx-mxfp8

MLX quantized version of numind/NuExtract3.

Quantization

  • mode: mxfp8
  • group_size: 32
  • bits: 8
  • dtype: source/default
  • quant_predicate: none

Usage 

pip install -U mlx-vlm
mlx_vlm.generate --model numind/NuExtract3-mlx-mxfp8 --prompt "your prompt"
Downloads last month
166
Safetensors
Model size
5B params
Tensor type
U32
·
BF16
·
MLX
Hardware compatibility
Log In to add your hardware

8-bit

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

Model tree for numind/NuExtract3-mlx-mxfp8

Base model

Qwen/Qwen3.5-4B-Base
Finetuned
Qwen/Qwen3.5-4B
Finetuned
numind/NuExtract3
Quantized
(18)
this model

Collection including numind/NuExtract3-mlx-mxfp8