iamraafay/deepseek-vl-1.3b-4bitill-qwen-1.5b

This model was converted to MLX format from mlx-community/deepseek-vl-1.3b-4bit using mlx-vlm version 0.1.13. 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 iamraafay/deepseek-vl-1.3b-4bitill-qwen-1.5b --max-tokens 100 --temp 0.0 --prompt "Describe this image." --image <path_to_image>