Post-Cutoff.com
  1. Home
  2. Models
  3. YuE2-3B

YuE2-3B

Multimodal Art Projection (M-A-P)currentmusicYuEopen weights

Self-reported WildSongBench best-of-8 6.9632 vs Suno v5 6.8721. English + Mandarin lyrics. Model card states ~4B parameters. HF repos created 2026-09-09; exact public announcement day not verified. Predecessor YuE (2025-01-28, arXiv 2503.08638).

Input
text, audio
Output
audio
License
cc-by-nc-4.0 (weights; commercial license available), apache-2.0 (code)
Verified
2026-09-29

How to call it

ProviderModel idEndpoint / URLDocs
Hugging Face—huggingface.co/m-a-p/YuE2-3B—
GitHub (inference code, agent skill)—github.com/multimodal-art-projection/YuE—
Hugging Face (community GGUF)—huggingface.co/audio-cpp/Yue2-3B-GGUF—

Notable capabilities (2)

Open-weights full-song generator from M-A-P (HKUST-led). Runs locally on one consumer GPU; weights download automatically on first use via the GitHub package.

Sources: https://github.com/multimodal-art-projection/YuE , https://huggingface.co/m-a-p/YuE2-3B

Timeline entry

  1. YuE2: open-weights song model that plans an editable score first, claims top WildSongBench score over Suno v5 ★★★

    The M-A-P research community (HKUST and partners) released YuE2, a ~3-4B open-weights song generator that first writes an editable melody-and-chord score (ABC notation) and then renders full songs with vocals and accompaniment at 48 kHz stereo, with zero-shot covers and conversational "agentic"…