Qwen2.5-Omni 3B

Parameters

3B

Published

Mar 26, 2025

Qwen2.5-Omni 3B is an AI model developed by Alibaba (China), first published in March 2025. It works in the multimodal, language, vision and 3 more domain, on tasks such as language modeling/generation, question answering, visual question answering and 8 more.

Epoch AI has no training-compute estimate for this model. The model has 3,000,000,000 parameters.

Access: Open weights (non-commercial). Its weights are openly available. It is built on top of Qwen2.5-3B. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Alibaba
Country of organization: China
Domain: Multimodal, Language, Vision, Video, Audio, Speech
Task: Language modeling/generation, Question answering, Visual question answering, Speech synthesis, Speech recognition (ASR), Speech-to-speech, Audio question answering, Speech-to-text, Text-to-speech (TTS), Video description, Image captioning
Compute estimation method: Operation counting
Parameters: 3,000,000,000
Model accessibility: Open weights (non-commercial)
Open weights: Yes
Base model: Qwen2.5-3B
Epoch confidence: Confident