Instructions to use mlx-community/Mistral-Small-24B-Instruct-2501-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Mistral-Small-24B-Instruct-2501-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Mistral-Small-24B-Instruct-2501-4bit mlx-community/Mistral-Small-24B-Instruct-2501-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Sync system prompt with parent
#1
by pcuenq HF Staff - opened
From what we know, a sensible system prompt is important for the model's performance, and these changes were performed in the parent model shortly after release.