---
license: apache-2.0
base_model: Qwen/Qwen3-Omni-30B-A3B-Instruct
pipeline_tag: text-generation
language:
- en
tags:
- text-generation
- multimodal
- vision
- audio
- zen
- zenlm
- hanzo
---

> **Status:** Superseded by [zenlm/zen3-omni](https://huggingface.co/zenlm/zen3-omni). Weights remain available for reproducibility.


# zen-omni

> Superseded by [zenlm/zen3-omni](https://huggingface.co/zenlm/zen3-omni) — canonical name.

Multimodal model supporting text, image, audio, and video understanding.

Repackaged from [Qwen/Qwen3-Omni-30B-A3B-Instruct](https://huggingface.co/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).