qwen3:32b

Family context: Qwen3 initial 2504 family

Publisher: Qwen Team

Qwen documents dense and mixture-of-experts releases in the initial Qwen3 family, with configurable thinking and direct-response modes. Later dated Instruct and Thinking releases are distinct variants.

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

Published family information

Initial dense sizes

0.6B, 1.7B, 4B, 8B, 14B and 32B Source

Initial mixture-of-experts sizes

30B-A3B and 235B-A22B Source

Publisher-described uses

• Multilingual instruction-following text and tool-using workflows described by Qwen. Source

Reference limitations

• A model tag without a dated checkpoint does not identify the later 2507 variant or establish its thinking mode or context 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 initial 2504 family official documentation — Qwen Team. Checked 2026-11-02.

Links

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

• Alibaba Cloud Qwen — official site
• Ollama
• Hugging Face
• Official model announcement / documentation

Where qwen3:32b comes from

Named in 2 observation pages

• 14B-32B local models — all 47 · V1
• Thinking-token re-observation — 14B-32B · V2