Qwen3-Omni-30B-A3B

Training compute

3.6×10²² FLOP

Parameters

35.3B

Published

Sep 22, 2025

Qwen3-Omni-30B-A3B is an AI model developed by Alibaba (China), first published in September 2025. It works in the multimodal, language, vision and 2 more domain, on tasks such as language modeling/generation, question answering, visual question answering and 6 more.

Training it took an estimated 3.6×10²² FLOP of compute (estimation method: operation counting). The model has 35,300,000,000 parameters. It was trained on roughly 2T 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: Multimodal, Language, Vision, Speech, Video
Task: Language modeling/generation, Question answering, Visual question answering, Image captioning, Video description, Speech recognition (ASR), Speech synthesis, Speech-to-text, Text-to-speech (TTS)
Training compute: 3.6×10²² FLOP
Compute estimation method: Operation counting
Parameters: 35,300,000,000
Dataset size: 2T
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Confident