Qwen 2.5 VL 32B Instruct

Downloads
Hugging Face
2.0M
462
Context
Long context
128K
License
license:apache-2.0
Updated
11/3/2025
by
Qwen

This model is designed for image-text-to-text tasks, supporting the English language. It utilizes the transformers library and is tagged as multimodal.

Image Model
OTHER
32B params

Quick Info

Released
3/21/2025
Framework
OTHER

Resources