Qwen3-VL
Vision-language flagship with 235B parameters, 22B active, in Instruct and Thinking versions.
Today, we officially launch the all-new Qwen3-VL series — the most powerful vision-language model in the Qwen family to date.
Official source
Qwen3-VL: Sharper Vision, Deeper Thought, Broader Actionqwen.ai · published