Qwen3 30B A3B Instruct 2507
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and agentic tool use.
Input
Output
Context
262K
Max Output
262K
Parameters
30B
Technical Specifications
Model TypeChat
Context Window262K
Max Output Tokens262K
Parameters30B
Training Cutoff—
Licenseapache-2.0
Capabilities
Input Modalities
text
Output Modalities
text
Features
function_callingjson_modereasoningstreamingtext_generation
Benchmarks
#25
Rank (Text)
+12/-12
arena text ci 95
1380
Arena Score (Text)
2,258
Votes (Text)
Resources & Links
Estimated GPU Requirements for Qwen3 30B A3B Instruct 2507
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.