Instructions to use numind/NuExtract3-mlx-6bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use numind/NuExtract3-mlx-6bits with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir NuExtract3-mlx-6bits numind/NuExtract3-mlx-6bits
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
| library_name: mlx | |
| base_model: numind/NuExtract3 | |
| base_model_relation: quantized | |
| tags: | |
| - mlx | |
| - mlx-vlm | |
| - quantized | |
| # 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 | |
| ```bash | |
| pip install -U mlx-vlm | |
| mlx_vlm.generate --model numind/NuExtract3-mlx-6bits --prompt "your prompt" | |
| ``` |