Instructions to use mlx-community/Mistral-Small-4-119B-2603-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Mistral-Small-4-119B-2603-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Mistral-Small-4-119B-2603-8bit mlx-community/Mistral-Small-4-119B-2603-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
mlx-community/Mistral-Small-4-119B-2603-8bit
This model was converted to MLX format from mistralai/Mistral-Small-4-119B-2603 using mlx-vlm version 0.4.0.
Refer to the original model card for more details on the model.
Use with mlx
pip install -U mlx-vlm
python -m mlx_vlm.generate --model mlx-community/Mistral-Small-4-119B-2603-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
- Downloads last month
- 168
Model size
34B params
Tensor type
BF16
·
U32 ·
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