# QwenLM/Qwen3

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Repository: https://github.com/QwenLM/Qwen3
Canonical: https://ross.abutalabs.com/products/qwen3
Language: Python
License Family: other
Last push: 2026-01-09T03:05:47+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 61, release rhythm 35, longevity 67
- inputs: {"age_days": 940, "days_push": 236, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 27560, forks 2044 (observed 2026-08-28T04:11:47.827869+00:00)

## What it is
Qwen3 is a family of open-weight large language models from Alibaba's Qwen team, with instruct and thinking variants in multiple sizes. The repository serves as the official hub with documentation, quickstart guides, and links to checkpoints on Hugging Face and ModelScope.

## Use cases
- download and run open-weight LLMs locally
- deploy a large language model with vLLM or SGLang
- fine-tune an LLM with SFT or RLHF
- quantize an LLM to GGUF, GPTQ, or AWQ
- build RAG or agent applications on top of an open model
- run a chat model on CPU or GPU with llama.cpp or Ollama

## When to choose
- you need open-weight LLM checkpoints with official inference and deployment guidance
- you want both instruct and reasoning (thinking) model variants
- you need multilingual models in sizes from 4B to 235B MoE

## When to avoid
- you need a hosted API rather than self-hosted model weights
- you want a ready-made application rather than model weights and docs
- you require a permissive license - the repo lists no license

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-inference, llm-training, machine-learning
- domain: large-language-models, artificial-intelligence, deep-learning
- platform: python, cross-platform
- tags: open-weights, model-family, huggingface, quantization, multilingual, reasoning-models, gpu

## Member repositories
- QwenLM/Qwen3 (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:47.827869+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:54:31.093699+00:00, confidence not recorded.
  - readme: https://github.com/QwenLM/Qwen3 (fetched 2026-08-28T04:11:47.827869+00:00, sha 82433e0aba82)
- Data as of 2026-08-30T08:39:29.467469+00:00.