opensource

github.com/QwenLM/Qwen Models & ML Research Open-source projectOpen source

Qwen is a series of chat and pretrained language models proposed by Alibaba Cloud.

github.com/QwenLM/Qwen
opensource homepage screenshot

About opensource

Qwen is an open-source repository from Alibaba Cloud that publishes the Qwen series of language models. It includes base pretrained models and chat models in 1.8B, 7B, 14B, and 72B parameter sizes. The base models were pretrained on up to 3 trillion tokens of multilingual data, with a focus on Chinese and English. The repository provides a quickstart, tutorials on finetuning and deployment, and demo instructions. Each model size has a listed maximum context length, ranging from 8K to 32K tokens, and the repository publishes minimum GPU memory figures for finetuning and generation.

The repository states that it is no longer actively maintained because of substantial codebase differences. The text points to Qwen2 as the newer project. The chat models are described as aligned with human preference using SFT and RLHF, but the text notes that the RLHF-aligned versions were not released yet. Use of the models is governed by Tongyi Qianwen license agreements included in the repository.

Key features

  • Base pretrained language models at 1.8B, 7B, 14B, and 72B sizes
  • Chat model variants built on the Qwen base models, including Int4 and Int8
  • Tutorials for full-parameter tuning, LoRA, and Q-LoRA finetuning
  • Deployment instructions using vLLM and FastChat
  • Demo instructions for a WebUI and a command-line interface
  • Information on tool use, agent use, and code interpreter applications
Best for: Researchers and developers who want to study, finetune, or deploy the earlier Qwen 1.8B to 72B models, particularly for Chinese and English language tasks.
Good for
  • Base models were pretrained on up to 3 trillion tokens of multilingual data, with a focus on Chinese and English.
  • Publishes minimum GPU memory figures for finetuning and generation for each model size.
  • Includes quickstart, quantization details, and inference performance statistics.
Watch out for
  • The repository is no longer actively maintained because of substantial codebase differences; Qwen2 is the newer project.
  • The text states that the RLHF-aligned chat models were not released yet.
  • Use is governed by the Tongyi Qianwen license agreements included in the repository, which should be reviewed before use.

opensource at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 6, 2026 · Online when checked
Listed
Oct 5, 2026

opensource alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in Models & ML Research

Well-known listings from the same topic.

All 69

opensource FAQ

Which Qwen model sizes does this repository cover?
The repository covers the base models Qwen-1.8B, Qwen-7B, Qwen-14B, and Qwen-72B, along with their chat model counterparts.
Is this repository still maintained?
No. The repository states that it is no longer actively maintained due to substantial codebase differences, and it directs readers to the Qwen2 repository.
Where can I find the license terms?
The repository includes the Tongyi Qianwen License Agreement and the Tongyi Qianwen Research License Agreement as files in the project.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing