Model reference · open weights

YuE2

Audio m-a-p Music / audio 1 build Non-commercial 3k dl/mo

YuE2 is an open-weight audio or speech model from m-a-p. YuE2-3B (BF16) weighs 7.3 GB; the smallest configuration that runs it is RTX 3060 12 GB.

For self-hosting, compare this build's requirements below with the GPU you plan to rent.

  • YuE2 is an open music generation model developed by m-a-p that converts lyrics and style prompts into complete songs with vocals and accompaniment.
  • The model features 3.6 billion parameters, supports a context length of 24,576 tokens, and operates in Chinese and English.
  • It is distributed under the cc-by-nc-4.0 license and can run locally on a 24GB GPU to produce 48 kHz stereo audio.

Summary of the m-a-p/YuE2-3B model card, 2026-10-01

What it is

Released bym-a-p
Released2026-09-09
Parameters3.6B
VRAM7.3 GB for the weights

What it runs on

Memory and cards for YuE2-3B (BF16)

7.3 GBweights, file size
1.6 GBruntime overhead
CardOne streamMemory
RTX 3060 12 GBfits11.6 GB
RTX 4060 Ti 16 GBfits15.4 GB
RTX 3090 24 GBfits23.4 GB
RTX 4090 24 GBfits23.4 GB
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

From the model card

What m-a-p says about YuE2

Read the model card

  · · · · · ·            

YuE2 is an open music generation model with frontier song quality competitive with Suno v5/v6. Turn lyrics and a style prompt into a complete song with vocals and accompaniment, then shape its melody and chords through an editable score.

State-of-the-art results on WildSongBench. YuE2 (best-of-8) achieves the highest SongBench average among all evaluated open and proprietary models: 6.9632, compared with 6.8721 for Suno v5, 6.5562 for Suno v6, and 6.4195 for Suno v6 Wild.

Frontier song quality and text alignment on 192 WildSongBench prompts. YuE2 uses symbolic planning; Bo8 means best-of-8.

September 12, 2026 comparison: 17 settings, including Suno v6 and Suno v6 Wild. Vector PDF · SVG · All nine metrics and protocols · Full-precision CSV.

  • Compose and edit: melody + chords, melody-only, or direct generation; bring your own ABC score.
  • Edit with an agent: turn musical feedback into score, style and lyric revisions, then let YuE2 render the next version. Hear the editing process.
  • Run locally: 48 kHz stereo songs on a 24GB GPU, without quantization.
  • Build on it: Hugging Face loading, text guidance (CFG), and separate planning and synthesis APIs.

One AR–NAR Mixture-of-Transformers backbone writes the score and semantic tokens, then generates acoustic latents through flow matching. The VAE turns them into stereo audio.

🎧 Listen to YuE2

🎶 Text-to-music

Original songs generated from lyrics and a style prompt.

Cyber Metal · English · 5:00

今晚不眠 · Mandarin funk / nu-disco · 3:24

Passion · English rock · 3:55

All three songs use 🤗 YuE2-Vae.

🎙️ Cover songs

Existing songs reimagined in a new style.

Make your own cover →

Auld Lang Syne · Jazz-funk cover · 3:10

最炫民族风 · Ballad cover · 4:45

Jingle Bells · Heavy metal cover · 1:09

🤖 Agentic editing

Explore the agentic editing demo →

Follow The Last Train through 9 steps and 14 versions, from Mandarin pop to English jazz with modern harmony and a saxophone solo built around two complete statements of “Twinkle, Twinkle, Little Star.” Hear the full songs and inspect the conversation, scores, prompts and lyrics at each step.

Try editing with an agent →

🚀 Quick start

Linux · Python 3.10+ · 24GB NVIDIA GPU with BF16 support. Install the inference package:

python -m pip install huggingface-hub==0.36.2
hf download m-a-p/YuE2-3B yue2_infer-0.1.5-py3-none-any.whl --local-dir .
python -m pip install ./yue2_infer-0.1.5-py3-none-any.whl

Create · Cover · Edit & agentic edit

Load the pipeline once for the examples below:

from pathlib import Path
from yue2 import YuE2Pipeline

pipe = YuE2Pipeline.from_pretrained("m-a-p/YuE2-3B", device="cuda")

🎶 Create

Turn a style prompt and lyrics into a complete song with vocals and accompaniment.

Use the style and full lyrics from 今晚不眠, the funk / nu-disco demo above.

import json
from huggingface_hub import hf_hub_download

repo = "m-a-p/YuE2-3B"
prompt_path = hf_hub_download(repo, "examples/tonight-awake.json")
demo = json.loads(Path(prompt_path).read_text(encoding="utf-8"))
style, lyrics = demo["style"], demo["lyrics"]

song = pipe(style=style, lyrics=lyrics, cot="full", seed=demo["seed"])
song.save("song.flac")
song.save_artifacts("outputs/song")  # ABC, tokens, latents, audio and settings

Defaults are ready to use: cot="full" and 🤗 YuE2-Vae.

OptionWhat it does
cot="full"Melody + chord planning (default)
cot="melody"Melody-only planning; recommended for covers
cot="off"Generate without a symbolic plan
cfg_scale=1.2Experiment with stronger text guidance

🎙️ Cover

Start from an existing recording and give it a new arrangement.

For covers, we recommend melody-only mode (cot="melody").

  1. Get the score: transcribe the existing song with 🤗 SheetSage2 and save its melody ABC without chord symbols as melody.abc.
  2. Get the lyrics: ask an agent to find them online, or transcribe the singing with Qwen3-ASR or the Gemini API. Check the words, organize them into sections matching the recording, and save them as cover_lyrics.txt.
  3. Choose a target style and generate: review or edit the score and lyrics, then supply them to YuE2 with cot="melody" and your target style prompt.

Run the transcription tools in their own environments, then use the YuE2 pipeline:

cover = pipe(
    style="Jazz-funk, warm lead vocal, Rhodes piano, electric bass, tight drums",
    lyrics=Path("cover_lyrics.txt").read_text(encoding="utf-8"),
    abc=Path("melody.abc").read_text(encoding="utf-8"),
    cot="melody", seed=831001,
)
cover.save("cover.flac")
cover.save_artifacts("outputs/cover")

cot="melody" does not remove chord symbols automatically. Use cot="full" if you want to supply the original or edited harmony as well.

🎼 Edit & agentic edit

Edit the ABC yourself, or give an agent the score, original prompt and lyrics, and your requested changes. The agent can reharmonize, develop a solo, or adapt the lyrics and style; YuE2 renders each revision. [Hear the multi-

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

Running it yourself

Run it on a rented GPU

Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel, then Templates → YuE2: Text to Music: it loads ComfyUI's own build of this model, the files above.

# on your rented machine (the ssh line is on its page in the console)
# get REPO FILE FOLDER: one file into /workspace/models/FOLDER, where ComfyUI loads it from
get() { hf download "$1" "$2" --local-dir /workspace/hf-files && mkdir -p "/workspace/models/$3" && mv "/workspace/hf-files/$2" "/workspace/models/$3/$4"; }

# the files of the template “YuE2: Text to Music” (3.7 GB)
get Comfy-Org/YuE2 checkpoints/yue2_3b_int8_convrot.safetensors checkpoints

start-comfyui
Renting a GPU: connect, tunnels, ComfyUI
# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST, PORT and BOOKING are your machine's, from its page in the console
ssh -o HostKeyAlias=axforge-BOOKING -o StrictHostKeyChecking=accept-new -L 8188:localhost:8188 dev@HOST -p PORT
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms