← All models
Qwen3 VL 30B A3B Instruct
qwen
Open vision-language MoE model for image and video understanding, documents, and visual agents
- Family
- qwen
- Providers
- 7
- Context
- 262,144
- Output
- 32,768
- Knowledge
- -
- Weights
- Open
- Input
- textimagevideo
- Output
- text
- Release date
- 2025-10-04
- Updated
- 2025-10-04
Providers
Source: models.dev