# QwenLM/Qwen3.8

Qwen3.8 is the large language model series developed by Qwen team, Alibaba Group.

Repository: https://github.com/QwenLM/Qwen3.8
Canonical: https://ross.abutalabs.com/products/qwen38
Homepage: https://qwen.ai
License: Apache-2.0
License Family: permissive
Last push: 2026-08-17T05:17:40+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 25
- inputs: {"age_days": 356, "days_push": 16, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3976, forks 291 (observed 2026-08-28T04:08:30.855397+00:00)

## What it is
Official repository for the Qwen3.8 open large language model series from Alibaba's Qwen team, providing release information, documentation, and community discussion for Qwen3.5, Qwen3.6, and Qwen3.8. The models emphasize coding, agentic task execution, and tunable reasoning depth, with weights distributed via Hugging Face and ModelScope.

## Use cases
- run a powerful open-weight LLM locally
- build autonomous agents that complete multi-step tasks
- integrate a frontier-class coding assistant into my dev tools
- download Qwen model weights from Hugging Face
- tune reasoning effort for my chatbot
- deploy an open LLM for enterprise applications

## When to choose
- you need an Apache-2.0 licensed frontier-class open model
- you want strong agentic coding and long-horizon task execution
- you need flexible reasoning-depth control in your LLM stack

## When to avoid
- you need the actual model code or training pipeline - this repo is primarily an information hub
- you need a small model for edge devices
- you require non-permissive licensing for commercial redistribution

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-inference, machine-learning, agent-framework, chatbot
- domain: large-language-models, artificial-intelligence, deep-learning
- platform: python, cloud, cross-platform
- tags: open-weights, qwen, alibaba, multimodal, reasoning, model-release, hugging-face, ai-agents, gpu

## Member repositories
- QwenLM/Qwen3.8 (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:30.855397+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 2026-08-29T18:24:19.201015+00:00, confidence not recorded.
  - readme: https://github.com/QwenLM/Qwen3.8 (fetched 2026-08-28T04:08:30.855397+00:00, sha e14431b75cd5)
  - homepage: https://qwen.ai (fetched 2026-08-29T09:17:57.866261+00:00, sha f3ffa38c264f)
- Data as of 2026-08-30T08:39:29.467469+00:00.