Qwen3-Next-80B-A3B

Training compute

2.7×10²³ FLOP

Parameters

80B

Published

Sep 10, 2025

Qwen3-Next-80B-A3B is an AI model developed by Alibaba (China), first published in September 2025. It works in the language domain, on tasks such as language modeling/generation, question answering, system control and code generation.

Training it took an estimated 2.7×10²³ FLOP of compute (estimation method: operation counting). The model has 80,000,000,000 parameters. It was trained on roughly 15T datapoints.

Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Alibaba
Country of organization: China
Domain: Language
Task: Language modeling/generation, Question answering, System control, Code generation
Training compute: 2.7×10²³ FLOP
Compute estimation method: Operation counting
Parameters: 80,000,000,000
Dataset size: 15T
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Confident