YuE2-3B open music model lands on Hugging Face, tops WildSongBench over Suno v5/v6
AdinaYakup · x · 2026-09-14
YuE2-3B from the M-A-P community is now on Hugging Face (cc-by-nc-4.0, Chinese and English). On 192 WildSongBench prompts it scores 6.9632 (best-of-8), beating Suno v5 (6.8721), Suno v6 (6.5562) and Suno v6 Wild (6.4195) across all open and proprietary models. Features: lyrics+style to full song, editable ABC scores for melody/chords, agent-based editing, and unquantized local inference on a 24GB GPU. Built on an AR–NAR Mixture-of-Transformers backbone with flow matching and a VAE for 48kHz stereo output.
Related event: Open-Source Music Model YuE2 Released, Beating Suno on Benchmarks(2 posts)→
More from Multimodal
- Maestro: an all-in-one local AI creative studio, 1-click install via Pinokio — cocktailpeanut · 2026-09-14
- Ambient distills long-video perception into a sub-2B model, topping egocentric video QA — ambient-intelligence-labs · 2026-09-14
- React Native Virtual Try-On App Ships: Segmind vs fal.ai VTON Tested — Visual_Art523 · 2026-09-14
- LTX 2.5 Dev Creepily Emails Everyone Who Pulled the Weights — SHEEP_PIZZA · 2026-09-14
- AI-Generated Actor Tilly Interviewed on Good Morning Britain, Awkward Pauses and All — ZeroStateReflex · 2026-09-14
- SeedVR2 takes 12+ hours to upscale a 2-minute clip on an RTX 5080 — is this normal? — Afraid-Woodpecker664 · 2026-09-14