YuE
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
- Hong Kong University of Science and Technology (HKUST),Multimodal Art Projection (MAP)
- Organisation type
- Academia,Research collective
- Country
- Hong Kong, China
- Published
- 11 March 2025
- Authors
- Ruibin Yuan, Hanfeng Lin, Shuyue Guo, Ge Zhang, Jiahao Pan, Yongyi Zang, Haohe Liu, Yiming Liang, Wenye Ma, Xingjian Du, Xinrun Du, Zhen Ye, Tianyu Zheng, Yinghao Ma, Minghao Liu, Zeyue Tian, Ziya Zhou, Liumeng Xue, Xingwei Qu, Yizhi Li, Shangda Wu, Tianhao Shen, Ziyang Ma, Jun Zhan, Chunhui Wang, Yatian Wang, Xiaowei Chi, Xinyue Zhang, Zhenzhu Yang, Xiangzhou Wang, Shansong Liu, Lingrui Mei, Peng…
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Speech
- Task
- Music generation, Text-to-speech (TTS)
- Base model
- Llama 2-7B
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
- 7B
- Training data
- tokens
7B
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA H800 SXM5
- Chips used
- 512
- Power draw
- 703.3 kW
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
- Citations
- 65
Sources
Where this record came from and when it was last checked.
- Reference
- YuE: Scaling Open Foundation Models for Long-Form Music Generation
- Last updated
- 25 May 2026
What the numbers mean
About this model
YuE was published by Hong Kong University of Science and Technology (HKUST),Multimodal Art Projection (MAP), in the country recorded as Hong Kong, during March 2025. It comes out of an organisation categorised as academia,Research collective.
It works in the domain of Speech, and is recorded as performing the task of music generation, Text-to-speech (TTS).
Rather than being trained from scratch, it is derived from Llama 2-7B. That is why it shares the base model's general shape and size.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Answers
YuE — common questions
YuE— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
YuE— how many parameters does it have?
It has a parameter count of 7B. 7B. 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.
YuE— who created it?
It was published by Hong Kong University of Science and Technology (HKUST),Multimodal Art Projection (MAP), based in Hong Kong, an organisation categorised as academia,Research collective.
YuE— when was it released?
It was published in March 2025.
YuE— what is it used for?
It works in the domain of Speech, and is recorded as handling the task of music generation, Text-to-speech (TTS). These are the areas it was designed around; they describe intent rather than a hard boundary.
YuE— what GPU do I need to run it?
None. This 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.
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.