Model reference · open weights
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.
AxForge offerings: YuE2
Summary of the m-a-p/YuE2-3B model card, 2026-10-01
What it is
| Released by | m-a-p |
|---|---|
| Released | 2026-09-09 |
| Parameters | 3.6B |
| VRAM | 7.3 GB for the weights |
What it runs on
| Card | One stream | Memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From 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.
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.
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.
Existing songs reimagined in a new style.
Auld Lang Syne · Jazz-funk cover · 3:10
最炫民族风 · Ballad cover · 4:45
Jingle Bells · Heavy metal cover · 1:09
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.
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")
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.
| Option | What 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=1.2 | Experiment with stronger text guidance |
Start from an existing recording and give it a new arrangement.
For covers, we recommend melody-only mode (cot="melody").
melody.abc.cover_lyrics.txt.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 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
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
# 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