Qwen3-Omni-30B-A3B
by Alibaba
· QWEN3 family · released Sep 21, 2025
Open weights
Active
Alibaba's open-weight 'Thinker-Talker' omni-modal model that understands text, image, video and audio and responds with synchronized text and natural speech.
No pricing recorded for this model yet.
Specifications
| Model type | Multimodal |
|---|---|
| Architecture | MoE |
| Parameters | 30 (3 active) |
| Context window | 262.1K tokens |
| Max output | Not disclosed tokens |
| Knowledge cutoff | Not disclosed |
| License | Apache License 2.0 |
| Modalities | Text input Image input Audio input Video input Text output Audio output |
| Tags | Vision |
| End of life | Not disclosed |
| Weights | Download |
| Last verified | Not disclosed |