Home/Inference & Serving/Qwen

Qwen

QwenLM/Qwen

Official repo of Qwen, a large language model by Alibaba Cloud

GitHub

GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026

79views this month

22k stars1.9k forksLast push Mar 5, 2026 Python Apache-2.0

Decision brief

Qwen is a large language model developed by Alibaba Cloud, available in Python with support for PyTorch and Transformers. It offers Docker images for easy deployment and supports various deployment options including Open

Good fit when

When you need a large language model that supports Chinese language processing effectively.
If you are working with PyTorch and Transformers and want a model that integrates seamlessly with these frameworks.

Avoid when

If your project strictly requires models under a different license, as Qwen is under the Apache-2.0 License with specific commercial use agreements.
When you need a model that does not require CUDA 11.4 or above for GPU acceleration, as Qwen recommends this for optimal performance.

Requirements:: Requires Docker; Requires Python 3.8 and above.; PyTorch 1.12 and above is required, with 2.0 and above recommended.; Transformers 4.32 and above are required.; CUDA 11.4 and above are recommended for GPU users.

Observed Sep 18, 2026 · Source: enrich:decision_facts

Qwen alternatives Trust report

Qwen vs Qwen-VL Qwen vs Chinese-LLaMA-Alpaca Qwen vs Yi

Verify the decision

Maintenance and security

Full trust report

Maintenance: Slowing (196d since push); As of Sep 18, 2026
Provenance: Not a fork · Organization account; As of Sep 18, 2026
Security (OSV): 50 low (50 low); As of Sep 18, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install Qwen

PyPI

How it fits your stack(18)

Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.

Relationship graph

Optional deeper exploration of typed edges and category neighbours.

Similar tools

Same-category neighbours not already linked as typed edges.

qlora

QLoRA finetuning of quantized LLMs

11k★

Chinese-LLaMA-Alpaca-2

Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models

7.1k★

qwen3.6-windows-server

One-click Qwen3.6-27B inference tool for Windows

229★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Qwen is a large language model and chat model developed by Alibaba Cloud, available in Python with support for PyTorch and Transformers. It includes Docker images for easy deployment and supports various deployment options including OpenAI API, Web UI, and CLI demo.

Capability facts

Languages: python
Source: github.language · Sep 18, 2026

Graph entities

Smolagentsframework

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

OpenAI APIOpenAI API

Source: README excerpt (regex_v1, Sep 18, 2026)

nly need to install the driver and download model files to launch demos, deploy OpenAI API, and finetune the model.

Source link

Python runtimePython

Source: README excerpt (regex_v1, Sep 18, 2026)

* python 3.8 and above

Source link

README

Requirements python 3.8 and above pytorch 1.12 and above, 2.0 and above are recommended transformers 4.32 and above CUDA 11.4 and above are recommended (this is for GPU users, flash attention users, etc.) <br pip install csrc/rotary bash IMAGE NAME=qwenllm/qwen:cu117 PORT=8901 CH...

For agents

This page has a .md twin and JSON over the API.

/tools/qwenlm-qwen.md GET /api/graphcanon/tools/qwenlm-qwen GET /api/graphcanon/graph?tool=qwenlm-qwen