Qwen3 32B
Qwen
qwen/qwen3-32bQwen3 32B is a dense open-weight model from Alibaba's Qwen3 generation, supporting both reasoning and non-reasoning modes. It is a solid general-purpose choice for chat, coding, and agentic tasks where a mid-size dense model is preferred over MoE.
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.
Mathematical
#108 · top 29%
Life, Physical, & Social Science
#185 · top 47%
Medicine & Healthcare
#185 · top 51%
Software & IT Services
#187 · top 48%
Performance
Median latency and throughput measured across recent requests.
Throughput104 tok/s
Latency