Qwen3-235B-A22B-Instruct-2507
Flagship non-thinking Qwen3 refresh with 262K context, Apache 2.0.
About
Qwen3-235B-A22B-Instruct-2507 is the flagship instruct model of the Qwen3-2507 refresh, shipped July 21, 2025 as the non-thinking counterpart to the thinking line. The 235-billion-parameter mixture-of-experts model activates about 22B parameters per token and arrived with a 262K native context window, improved instruction following, stronger multilingual long-tail knowledge, and better alignment on subjective open-ended tasks than the original April 2025 Qwen3 release.
The 2507 refresh marked Qwen's move away from hybrid thinking toggles toward cleanly separated model lines, so teams can pick deliberative reasoning or instant instruction-following without prompt gymnastics. It is available on Hugging Face as Qwen/Qwen3-235B-A22B-Instruct-2507 under Apache 2.0, and it anchors the top end of the 2507 family above the 30B-A3B and 4B instruct variants.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 8/10
Scored 8/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 120; Trending score 84/100 from researcher assessment.
More in the qwen3 family
- Qwen3-Next-80B-A3B
- Qwen3-235B-A22B
- Qwen3-235B-A22B-2507
- Qwen3-4B-Instruct-2507
- Qwen3-8B
- Qwen3.5
- Qwen3 235B
- Qwen3-235B-A22B-Thinking-2507
- Qwen3-Omni-Flash
- Qwen3.6-27B
- Qwen3-32B
- Qwen3-Max
- Qwen3.8-Flash-Next
- Qwen3-Coder-Plus
- Qwen3
- Qwen3-0.6B
- Qwen3-4B
- Qwen3-Coder-Next
- Qwen3-4B-2507
- Qwen3-14B
- Qwen3-VL-30B-A3B
- Qwen3-1.7B
- Qwen3-Omni-30B-A3B