Alibaba · Qwen (Alibaba)
Qwen3-235B
ActiveBest open-weight large model (Apache 2.0); MoE 235B total / ~22B active with toggleable thinking mode.
About this version
Qwen3-235B is the latest open‑weight release in the Qwen family, launched on 1 March 2026 and currently active. It is an Apache 2.0‑licensed mixture‑of‑experts model comprising a total of 235 billion parameters, with about 22 billion parameters active at any time, and includes a toggleable “thinking mode.” The model supports a context window of up to 128 000 tokens, positioning it as the largest open‑weight large language model available.
- Context window
- 128K ctx
- Tier
- Open Weight
- Released
- Mar 1, 2026
Release & change timeline
1 event- Release
Qwen3-235B released
Part of the Qwen3 family launch (March 2026); open-weight MoE large model with hybrid reasoning.
Report an issue with Qwen (Alibaba)
Posts to your status feed
Pick the closest match below, edit the body, and post. Your report carries the #qwen tag automatically so it surfaces here + in the trending-tags rail. Reporting also follows Qwen (Alibaba) so you’ll get status updates.
Part of the Qwen (Alibaba) version timeline. Catch Me Up — everything that changed across AI & smart home ↗