Qwen3.5-35B-A3B
Qwen
qwen/qwen3.5-35b-a3bQwen3.5 35B-A3B is a sparse mixture-of-experts model from Alibaba's Qwen3.5 line (35B total, 3B active parameters), built for efficient general-purpose and agentic tasks at low inference cost.
Cost rate
0.3x
Context
262K
Released
Feb 25, 2026
Input
TextImageVideo
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Medicine & Healthcare
#134 · top 37%
Mathematical
#138 · top 37%
Business, Management, & Finance
#140 · top 36%
Life, Physical, & Social Science
#145 · top 37%
Performance
Median latency and throughput measured across recent requests.
Throughput169 tok/s
Latency