Comment by michaelt
9 days ago
qwen2.5-vl-72b-instruct seems perfectly happy outputting bounding boxes in my testing.
There's also a paper https://arxiv.org/pdf/2409.12191 where they explicitly say some of their training included bounding boxes and coordinates.
We're also looking to test qwen and other for the bounding box support. Simon Willison had a great demo page where he used Gemini 2.5 to draw bounding boxes, and the results were pretty impressive. It would probably be pretty easy to drop qwen into the same UI.
https://simonwillison.net/2025/Mar/25/gemini