How to run YuE (s1 7B) locally

HKUST / M-A-P · Text → music · 6B params · Apache-2.0 (commercial OK)

An open lyrics-to-song foundation model generating multi-minute tracks with vocals and accompaniment, an open answer to Suno.

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 24 GB of VRAM (~24GB for full song gen; long generations are heavy), via YuE (Transformers).
Rent a GPU — from $0.49/hr. Fits RTX A6000 48GB at the direct vendor price ($0 markup) — pay only for the minutes you generate.
Download the weights — free. Open weights at m-a-p/YuE-s1-7B-anneal-en-cot.

Note: generative-media models are billed per image / per second / per minute on hosted services — not per token. Running locally or on your own rented GPU is usually far cheaper and keeps your data on your machine.

Key facts

Does	Text → music
VRAM to run	~24 GB (~24GB for full song gen; long generations are heavy)
Download	~13 GB
Parameters	6B
License	Apache-2.0 (commercial use OK)
Run with	YuE (Transformers)

Get YuE (s1 7B) on Hugging Face →

More voice & audio models

Whisper large-v3 — Speech → text, ~10 GB VRAM
Whisper large-v3-turbo — Speech → text, ~6.0 GB VRAM
Kokoro-82M — Text → speech, ~1.0 GB VRAM
XTTS-v2 — Voice cloning, ~6.0 GB VRAM
MusicGen Large — Text → music, ~16 GB VRAM
Chatterbox — Text → speech, ~8.0 GB VRAM

Browse: all media models · chat / LLM models