Status: Superseded by zenlm/zen3-omni. Weights remain available for reproducibility.
zen-omni-30b-instruct
Superseded by zenlm/zen3-omni — canonical name.
Multimodal model supporting text, image, audio, and video understanding.
Repackaged from Qwen/Qwen3-Omni-30B-A3B-Instruct (apache-2.0, Alibaba Qwen). Not trained from scratch — a permissively-licensed redistribution for the OSS-clean Zen model line.
Specs
| Property | Value |
|---|---|
| Parameters | 30B total / 3B active (MoE) |
| Architecture | Qwen3-Omni MoE (Qwen3OmniMoeForConditionalGeneration) |
| Modality | text, image, audio, video |
License
apache-2.0. Upstream: Qwen/Qwen3-Omni-30B-A3B-Instruct by Alibaba Qwen (apache-2.0).