qwen3-coder:30b

Upstream reference: Qwen3-Coder-30B-A3B-Instruct

Publisher: Qwen Team, Alibaba Cloud

Qwen documents this mixture-of-experts coding model for repository-scale and tool-using development workflows, with a version-specific function-call format.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published upstream specifications

Total parameters

30.5 billion Source

Active parameters

3.3 billion Source

Native context

262,144 tokens Source

Generation mode

Non-thinking only Source

Upstream license label

Apache-2.0 Source

Publisher-described uses

• Coding assistants and development tools using the documented parser and templates. Source

Reference limitations

• The 1M extension requires YaRN; it is not the native context or a measured site runtime setting. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

• Qwen3-Coder-30B-A3B-Instruct official documentation — Qwen Team, Alibaba Cloud. Checked 2026-11-02.

Links

Recorded references do not establish downloadable weights, licensing or current availability.

• Alibaba Cloud Qwen — official site
• Ollama
• Hugging Face

Where qwen3-coder:30b comes from

Named in 1 observation page

• 14B-32B local models — all 47 · V1