[KongchangAI]
Model

Qwen3-Omni-30B-A3B

A multimodal large model in the Qwen series that supports audio, visual, and text input, with 30B parameters (3B activated parameters).

Timeline (last 90 days)

Nov 17

On the turn-end detection task, Marimba reaches an AUROC of 0.935, while the comparison models (Qwen3-Omni-30B-A3B, Qwen2-Audio-7B, FireRedAudio 10.6B) range between 0.54 and 0.79.

Unverified50%
Oct 12

Clef-omni is built on Alibaba's Qwen3-Omni-30B-A3B.

Unverified50%

All Facts (2)

Source Articles