Qwen3 Next 80B A3B Thinking

Qwen3 Next 80B A3B Thinking

Archived
Qwen🇨🇳qwen/qwen3-next-80b-a3b-thinking
Compare

The extended-reasoning variant of Qwen3-Next 80B-A3B, Alibaba's efficient next-generation MoE model, producing explicit chain-of-thought for harder reasoning and agentic tasks while retaining the architecture's low inference cost.

Released
Sep 11, 2025
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs

Performance

Median latency and throughput measured across recent requests.

Throughput136 tok/s
Latency0.79s

Latest news about Qwen3 Next 80B A3B Thinking

Recent articles and community posts, linked to their original sources.