Instructions to use garrison/Olmo-3-32B-Think-mlx-6Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use garrison/Olmo-3-32B-Think-mlx-6Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Olmo-3-32B-Think-mlx-6Bit garrison/Olmo-3-32B-Think-mlx-6Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
| { | |
| "_from_model_config": true, | |
| "eos_token_id": 100257, | |
| "pad_token_id": 100277, | |
| "transformers_version": "4.57.1" | |
| } | |