Qwen3-Omni-30B-A3B-Instruct
by Alibaba
· Qwen3-Omni family · released Sep 24, 2025
Open weights
Active
Open-weights end-to-end omni-modal model using a Thinker-Talker architecture for real-time speech-in/speech-out conversation plus image and video understanding.
No pricing recorded for this model yet.
Specifications
| Model type | Multimodal |
|---|---|
| Architecture | MoE |
| Parameters | 30 (3 active) |
| Context window | Not disclosed 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 | Agentic Vision |
| End of life | Not disclosed |
| Weights | Download |
| Last verified | Not disclosed |