Qwen3 235B A22B
Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and code tasks, and a "non-thinking" mode for general conversational efficiency.
Input
Output
Context
41K
Max Output
41K
Parameters
235B
Technical Specifications
Model TypeChat
Context Window41K
Max Output Tokens41K
Parameters235B
Training Cutoff—
Licenseapache-2.0
Capabilities
Input Modalities
text
Output Modalities
text
Features
function_callingjson_modereasoningstreamingtext_generation
Benchmarks
#37
Rank (Text)
+5/-5
arena text ci 95
1365
Arena Score (Text)
20,489
Votes (Text)
Resources & Links
Estimated GPU Requirements for Qwen3 235B A22B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.