Comment by simonw

This model is available for MLX now, in various different sizes.

I ran https://huggingface.co/mlx-community/Qwen2.5-VL-32B-Instruct... using uv (so no need to install libraries first) and https://github.com/Blaizzy/mlx-vlm like this:

  uv run --with 'numpy<2' --with mlx-vlm \
    python -m mlx_vlm.generate \
      --model mlx-community/Qwen2.5-VL-32B-Instruct-4bit \
      --max-tokens 1000 \
      --temperature 0.0 \
      --prompt "Describe this image." \
      --image Mpaboundrycdfw-1.png

That downloaded an ~18GB model and gave me a VERY impressive result, shown at the bottom here: https://simonwillison.net/2025/Mar/24/qwen25-vl-32b/