hugpadhugpad

Qwen / Qwen3-VL-4B-Instruct

Vision4.4B4.1M521Updated Oct 15, 2025
Hugging Face

Downloads

4.1M

Likes

521

Last updated

Oct 15, 2025

License

apache-2.0

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • qwen3_vl
  • image-text-to-text
  • conversational

Technical specifications

Parameters4.4B
Librarytransformers
LanguagesNot available
Licenseapache-2.0