Qwen3-Omni-Flash
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Alibaba
- Organisation type
- Industry
- Country
- China
- Published
- 22 September 2025
- Authors
- Jin Xu, Zhifang Guo, Hangrui Hu, Yunfei Chu, Xiong Wang, Jinzheng He, Yuxuan Wang, Xian Shi, Ting He, Xinfa Zhu, Yuanjun Lv, Yongqi Wang, Dake Guo, He Wang, Linhan Ma, Pei Zhang, Xinyu Zhang, Hongkun Hao, Zishan Guo, Baosong Yang, Bin Zhang, Ziyang Ma, Xipin Wei, Shuai Bai, Keqin Chen, Xuejing Liu, Peng Wang, Mingkun Yang, Dayiheng Liu, Xingzhang Ren, Bo Zheng, Rui Men, Fan Zhou, Bowen Yu, Jianxin…
What it does
The problem areas the model was built for. A model can carry several of each.
- 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)
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 35.3B
- Training data
- tokens
Audio Encoder AuT 650M Vision Encoder SigLIP2-So400M 540M Thinker MoE Transformer 30B-A3B Talker MoE Transformer 3B-A0.3B MTP Dense Transformer 80M Code2wav ConvNet 200M
"our AuT (Audio Transformer) encoder, trained from scratch on 20 million hours of supervised audio" "The second phase of pretraining utilizes a large-scale dataset containing approximately 2 trillion tokens, with the following distribution across modalities: text (0.57 trillion), audio (0.77 trillion), image (0.82 trillion), video (0.05 trillion), and video-audio (0.05 trillion)"
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 3.6 × 10²² FLOP
- How it was established
- Operation counting
6 FLOP/parameter/token * 3000000000 active parameters * 2000000000000 tokens = 3.6e+22 FLOP
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
- Training code
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Qwen3-Omni Technical Report
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Qwen3-Omni-Flash was published by Alibaba, in China, in September 2025. It comes out of industry.
It works in Multimodal, Language, Vision, Speech, Video, and is recorded as doing language modeling/generation, Question answering, Visual question answering, Image captioning, Video description, Speech recognition (ASR), Speech synthesis, Speech-to-text, Text-to-speech (TTS).
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
The training run consumed about 3.6 × 10²² FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
Answers
Qwen3-Omni-Flash — common questions
What GPU do I need to run Qwen3-Omni-Flash?
None. Qwen3-Omni-Flash is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
Is Qwen3-Omni-Flash open source?
No. Qwen3-Omni-Flash has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Qwen3-Omni-Flash have?
Qwen3-Omni-Flash has 35.3B parameters. Audio Encoder AuT 650M Vision Encoder SigLIP2-So400M 540M Thinker MoE Transformer 30B-A3B Talker MoE Transformer 3B-A0.3B MTP Dense Transformer 80M Code2wav ConvNet 200M. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
Who created Qwen3-Omni-Flash?
Qwen3-Omni-Flash was published by Alibaba, based in China, categorised as industry.
When was Qwen3-Omni-Flash released?
Qwen3-Omni-Flash was published in September 2025.
What is Qwen3-Omni-Flash used for?
Qwen3-Omni-Flash works in Multimodal, Language, Vision, Speech, Video, and is recorded as handling language modeling/generation, Question answering, Visual question answering, Image captioning, Video description, Speech recognition (ASR), Speech synthesis, Speech-to-text, Text-to-speech (TTS). These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train Qwen3-Omni-Flash?
Around 3.6 × 10²² FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.