Qwen2.5-VL-32B: Smarter and Lighter

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/

Does quantised MLX support vision though?

Is UV the best way to run it?

uv is just a Python package manager. No idea why they thought it was relevant to mention that

Because that one-liner will result in the model instantly running on your machine, which is much more useful than trying to figure out all the dependencies, invariably failing, and deciding that technology is horrible and that all you ever wanted was to be a carpenter.