Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
| Date | Stars |
|---|---|
| 2026-08-03 | 3924 |
| 2026-08-12 | 3947 |
| 2026-08-18 | 3960 |
| 2026-08-19 | 3962 |
| 2026-08-20 | 3966 |
| 2026-08-21 | 3968 |
| 2026-08-22 | 3970 |
| 2026-08-23 | 3971 |
| 2026-08-24 | 3972 |
| 2026-08-25 | 3975 |
| 2026-08-26 | 3979 |
| 2026-08-27 | 3981 |
| 2026-08-28 | 3985 |
| 2026-08-29 | 3986 |
| 2026-08-30 | 3988 |
| 2026-08-31 | 3990 |
| 2026-09-01 | 3993 |
| 2026-09-02 | 3996 |
| 2026-09-03 | 3999 |
| 2026-09-04 | 4000 |
| 2026-09-06 | 4001 |
| 2026-09-07 | 4002 |
| 2026-09-08 | 4005 |
| 2026-09-10 | 4006 |
| 2026-09-11 | 4007 |
| 2026-09-12 | 4009 |
| 2026-09-13 | 4009 |
| 2026-09-15 | 4010 |
| 2026-09-16 | 4011 |
| 2026-09-17 | 4012 |
| 2026-09-18 | 4012 |
| 2026-09-19 | 4015 |
| 2026-09-20 | 4017 |
| 2026-09-21 | 4021 |
| 2026-09-22 | 4024 |
| 2026-09-23 | 4026 |
| 2026-09-24 | 4029 |
| 2026-09-25 | 4029 |
| 2026-09-26 | 4030 |
| 2026-09-27 | 4031 |
| 2026-09-28 | 4032 |
| 2026-09-29 | 4034 |
| 2026-09-30 | 4035 |
| 2026-10-01 | 4036 |
| 2026-10-02 | 4037 |
| 2026-10-03 | 4038 |
| 2026-10-04 | 4037 |
| 2026-10-05 | 4039 |
| 2026-10-06 | 4041 |
| 2026-10-07 | 4040 |
| 2026-10-08 | 4042 |
| 2026-10-10 | 4042 |
| 2026-10-12 | 4046 |
| 2026-10-13 | 4050 |
| 2026-10-14 | 4054 |
| 2026-10-15 | 4058 |
| 2026-10-16 | 4059 |
| 2026-10-17 | 4060 |
| 2026-10-18 | 4061 |
| 2026-10-19 | 4062 |
| 2026-10-20 | 4063 |
| 2026-10-21 | 4067 |
| 2026-10-22 | 4071 |
| 2026-10-23 | 4072 |
| 2026-10-24 | 4073 |
| 2026-10-25 | 4074 |
| 2026-10-26 | 4077 |
| 2026-10-27 | 4082 |
| 2026-10-28 | 4083 |
| 2026-10-29 | 4084 |
| 2026-10-30 | 4089 |
| 2026-10-31 | 4090 |
| 2026-11-01 | 4092 |
| 2026-11-02 | 4094 |
| 2026-11-04 | 4093 |
Today
-1 stars today
This week
+10 stars this week
This month
+54 stars this month
Momentum
0.0
growth rate 0.24%/day
# Qwen3-Omni
<br>
<p align="center">
<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com//Qwen3-Omni/qwen3_omni_logo.png" width="400"/>
<p>
<p align="center">
💜 <a href="https://chat.qwen.ai/"><b>Qwen Chat</b></a>   |   🤗 <a href="https://huggingface.co/collections/Qwen/qwen3-omni-68d100a86cd0906843ceccbe">Hugging Face</a>   |   🤖 <a href="https://modelscope.cn/collections/Qwen3-Omni-867aef131e7d4f">ModelScope</a>   |   📑 <a href="https://qwen.ai/blog?id=65f766fc2dcba7905c1cb69cc4cab90e94126bf4&from=research.latest-advancements-list">Blog</a>   |   📚 <a href="https://github.com/QwenLM/Qwen3-Omni/tree/main/cookbooks">Cookbooks</a>   |   📑 <a href="https://arxiv.org/pdf/2509.17765">Paper</a>  
<br>
🖥️ <a href="https://huggingface.co/spaces/Qwen/Qwen3-Omni-Demo">Hugging Face Demo</a>   |    🖥️ <a href="https://modelscope.cn/studios/Qwen/Qwen3-Omni-Demo">ModelScope Demo</a>   |   💬 <a href="https://github.com/QwenLM/Qwen/blob/main/assets/wechat.png">WeChat (微信)</a>   |   🫨 <a href="https://discord.gg/CV4E9rpNSD">Discord</a>   |   📑 <a href="https://help.aliyun.com/zh/model-studio/user-guide/qwen-omni">API</a>
</p>
We release **Qwen3-Omni**, the natively end-to-end multilingual omni-modal foundation models. It is designed to process diverse inputs including text, images, audio, and video, while delivering real-time streaming responses in both text and natural speech. Click the video below for more information 😃
<details open>
<summary>English Version</summary>
<a href="https://youtu.be/_zdOrPju4_g" target="_blank">
<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Omni/videocover.png" alt="Open English Video"/>
</a>
</details>
<details>
<summary>Chinese Version</summary>
<a href="https://youtu.be/Wtjsw5deXfQ" target="_blank">
<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Omni/videocover.png" alt="打开中文视频"/>
</a>
</details>
## News
* 2025.09.26: ⭐️⭐️⭐️ Qwen3-Omni reaches top-1 on Hugging Face Trending!
* 2025.09.22: 🎉🎉🎉 We have released [Qwen3-Omni](https://huggingface.co/collections/Qwen/qwen3-omni-68d100a86cd0906843ceccbe). For more details, please check our [blog](https://qwen.ai/blog?id=65f766fc2dcba7905c1cb69cc4cab90e94126bf4&from=research.latest-advancements-list)!
## Contents <!-- omit in toc -->
- [Overview](#overview)
- [Introduction](#introduction)
- [Model Architecture](#model-architecture)
- [Cookbooks for Usage Cases](#cookbooks-for-usage-cases)
- [QuickStart](#quickstart)
- [Model Description and Download](#model-description-and-download)
- [Transformers Usage](#transformers-usage)
- [vLLM Usage](#vllm-usage)
- [DashScope API Usage](#dashscope-api-usage)
- [Usage Tips (Recommended Reading)](#usage-tips-recommended-reading)
- [Interaction with Qwen3-Omni](#interaction-with-qwen3-omni)
- [Online Demo](#online-demo)
- [Real-Time Interaction](#real-time-interaction)
- [Launch Local Web UI Demo](#launch-local-web-ui-demo)
- [Docker](#-docker)
- [Evaluation](#evaluation)
- [Performance of Qwen3-Omni](#performance-of-qwen3-omni)
- [Setting for Evaluation](#setting-for-evaluation)
- [Citation](#citation)
## Overview
### Introduction
<p align="center">
<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Omni/q3o_introduction.png" width="90%"/>
<p>
Qwen3-Omni is the natively end-to-end multilingual omni-modal foundation models. It processes text, images, audio, and video, and delivers real-time streaming responses in both text and natural speech. We introduce several architectural upgrades to improve performance and efficiency. Key features:
* **State-of-the-art across modalities**: Early text-first pretraining and mixed multimodal training provide native multimodal support. While achieving strong audio and audio-video results, unimodal text and image perfExcerpt of 101,153 characters
Read on GitHub
Xiong Wang · Alibaba Qwen Team · China
10
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c216f7ea255d47a3, llm:Repository description: 'Qwen3-omni is a natively end-to-end, omni-modal LLM ... capable of understanding text, audio, images, and video, as well as generating speech in real time.'
matched fp:c216f7ea255d47a3, llm:Repository description: 'Qwen3-omni is a natively end-to-end, omni-modal LLM ... capable of understanding text, audio, images, and video, as well as generating speech in real time.'
matched fp:c216f7ea255d47a3, llm:Repository description: 'Qwen3-omni is a natively end-to-end, omni-modal LLM ... capable of understanding text, audio, images, and video, as well as generating speech in real time.'
matched fp:c216f7ea255d47a3, llm:Repository description: 'Qwen3-omni is a natively end-to-end, omni-modal LLM ... capable of understanding text, audio, images, and video, as well as generating speech in real time.'