QwenLM/Qwen3
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
The project lists 46 contributors on GitHub.
Use Cases & Benefits
- Provides a series of large language models optimized for instruction following, reasoning, coding, and long-context understanding.
- Delivers state-of-the-art reasoning and multi-language capabilities with support for ultra-long context inputs up to 1 million tokens.
- Use for building advanced chatbots requiring deep logical reasoning and multi-turn dialogue with human-like alignment.
- Use for deploying large-scale inference services with frameworks like SGLang, vLLM, and TensorRT-LLM on diverse hardware.
- Use for fine-tuning and customizing LLMs with frameworks such as Axolotl and LLaMA-Factory for domain-specific applications.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
No license detected
No license file detected by GitHub: unless the project grants one elsewhere, the default is all rights reserved.
Community files
- README: present
Watch-outs
- Warning: No license file detected by GitHub: unless the project grants one elsewhere, you generally have no permission to use, modify or distribute the code.
- No commits in the last six months (last push Jan 2026).
- No GitHub releases; pin a commit or tag instead of a release.
General guidance from repository metadata, not legal advice. How we score
From the README
🖥️ Demo   |   💬 WeChat (微信)   |   🫨 Discord  
Visit our Hugging Face or ModelScope organization (click links above), search checkpoints with names starting with
Qwen3-or visit the Qwen3 collection, and you will find all you need! Enjoy!Over the past three months, we continued to explore the potential of the Qwen3 families and we are excited to introduce the updated Qwen3-2507 in two variants, Qwen3-Instruct-2507 and Qwen3-Thinking-2507, and three sizes, 235B-A22B, 30B-A3B, and 4B.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
2.1K+65
Open issues
69+5
Compared with peers in LLM
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 15, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| DietrichGebert/ponytail | 196.4K | +5.4K | 59 | 23 days ago |
| firecrawl/firecrawl | 206.2K | +5.4K | 52 | 155 days ago |
| affaan-m/ECC | 308.4K | +5.2K | 62 | 51 days ago |
| Tencent/LoopForge | 5.5K | +4.6K | 65 | 1 day ago |
| tashfeenahmed/freellmapi | 56.2K | +3.8K | 45 | today |
| QwenLM/Qwen3 | 27.7K | — | 33 | — |
| Category median | 196.4K | +5.2K | 59 | — |
Also by QwenLM
Other repositories from this maintainer that GStars tracks
- TypeScript30.8K stars
qwen-code
An open-source AI coding agent that lives in your terminal.
- Python22.0K stars
Qwen
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
- Jupyter Notebook20.2K stars
Qwen3-VL
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
- Python17.3K stars
Qwen-Agent
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
- Python16.9K stars
Qwen3-Coder
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.
Discover Repositories
Search across tracked repositories by name or description