Open music model YuE2 (3B) beats Suno v5/v6 on WildSongBench, runs on a 24GB GPU
AdinaYakup · x · 2026-09-14
The M-A-P community released YuE2, an open 3B music generation model that produces full 48kHz stereo songs locally on a 24GB GPU. Its best-of-8 score of 6.9632 tops WildSongBench ahead of Suno v5 (6.8721) and Suno v6 (6.5562). It supports editable ABC scores for melody and chords, style transfer of existing melodies, and an agent-driven editing loop. Architecture: an AR–NAR Mixture-of-Transformers backbone writes score and semantic tokens, with flow matching generating acoustic latents.
Related event: Open-Source Music Model YuE2 Beats Suno v5/v6 on WildSongBench(4 posts)→
More from Multimodal
- NVIDIA open-sources NemotronLabs RE-USE, a 9.6M-param multilingual speech denoiser — NVIDIAAI · 2026-10-31
- AI-generated fake trailer imagines a 1999 Dino Crisis movie with retro VHS feel — noizlab_studio · 2026-10-31
- Spatial Hub aggregates ~5000 public COLMAP-compatible spatial datasets for world models — janusch_patas · 2026-10-31
- Single image to walkable 3D Gaussian splat scene using World Labs Atlas and WebGPU — XRarchitect · 2026-10-31
- AI video reimagines Suicide Squad's Joker as a rapper in a full music-video treatment — Silver_War5476 · 2026-10-31
- 60+ community-made ChatGPT slash-style words turn one word into a full visual style — heyshrutimishra · 2026-10-31