mlx-community/llava-v1.6-mistral-7b-8bit

This model was converted to MLX format from llava-hf/llava-v1.6-mistral-7b-hf using mlx-vlm version 0.0.15. 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/llava-v1.6-mistral-7b-8bit --max-tokens 100 --temp 0.0