AI models
YuE
Parameters
7B
Published
Mar 11, 2025
YuE is an AI model developed by Hong Kong University of Science and Technology (HKUST) and Multimodal Art Projection (MAP) (Hong Kong and China), first published in March 2025. It works in the speech domain, on tasks such as music generation and text-to-speech (tts).
Epoch AI has no training-compute estimate for this model. The model has 7,000,000,000 parameters. Training ran on 512 NVIDIA H800 SXM5.
It is built on top of Llama 2-7B. The reference paper has 65 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Hong Kong University of Science and Technology (HKUST), Multimodal Art Projection (MAP)
- Country of organization
- Hong Kong, China
- Domain
- Speech
- Task
- Music generation, Text-to-speech (TTS)
- Parameters
- 7,000,000,000
- Training hardware
- NVIDIA H800 SXM5
- Chips used
- 512
- Training power draw
- 703.3 kW
- Base model
- Llama 2-7B
- Citations
- 65
- Epoch confidence
- Confident
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models