Instructions to use FurAbyss/Equinox-31B-oQ6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use FurAbyss/Equinox-31B-oQ6 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Equinox-31B-oQ6 FurAbyss/Equinox-31B-oQ6
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
metadata
license: apache-2.0
base_model:
- LatitudeGames/Equinox-31B
library_name: mlx
tags:
- oq
Equinox-31B-oQ6
This model was quantized from LatitudeGames/Equinox-31B using oQ (oMLX v0.3.8) mixed-precision quantization.
Quantization details
- Model type: gemma4
- Bits: 6
- Group size: 64
- Format: MLX safetensors