Qwen3 Next 80B A3B Instruct

Qwen3 Next 80B A3B Instruct

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

Qwen3-Next 80B-A3B Instruct is Alibaba's next-generation efficient mixture-of-experts model (80B total, 3B active), using a highly sparse architecture for strong general-purpose performance at low inference cost.

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

Performance

Median latency and throughput measured across recent requests.

Throughput91 tok/s
Latency1.2s

Best at

The categories where this model ranks highest.

Medicine & Healthcare

#134 · top 34%

Business, Management, & Finance

#146 · top 35%

Mathematical

#159 · top 39%

Software & IT Services

#160 · top 38%

DomainScoreRank
Software & IT Services1441#160
Writing, Literature, & Language1342#210
Life, Physical, & Social Science1417#167
Entertainment, Sports, & Media1325#214
Business, Management, & Finance1413#146
Mathematical1412#159
Legal & Government1409#162
Medicine & Healthcare1440#134

Latest news about Qwen3 Next 80B A3B Instruct

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