Qwen3 30B A3B
Qwen馃嚚馃嚦
qwen/qwen3-30b-a3bQwen3 30B-A3B is a smaller mixture-of-experts model (30B total, 3B active parameters) in Alibaba's Qwen3 line, offering good general-purpose capability at low inference cost thanks to its sparse activation.
Cost rate
0.1x
Context
131K
Released
Apr 28, 2025
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Business, Management, & Finance
#151 路 top 38%
Software & IT Services
#153 路 top 38%
Mathematical
#155 路 top 41%
Medicine & Healthcare
#169 路 top 46%
Performance
Median latency and throughput measured across recent requests.
Throughput107 tok/s
Latency