MiniMax Music 3 Open-Sources Weights: SOTA Song Generation on Consumer GPUs
multimodalart · x · 2026-08-14
MiniMax has released its latest music generation model, MiniMax Music 3, with open weights on Hugging Face.
Featuring an architecture of an 8B LLM and a 2.7B DiT, the model can generate full songs from prompts and lyrics, achieving state-of-the-art performance. Notably, it is highly hardware-friendly: via Diffusers or ComfyUI, users can run it locally on small consumer GPUs.
Related event: MiniMax Open-Sources Music 3, Generating 5-Minute Full Songs(13 posts)→
More from Multimodal
- Higgsfield Open-Sources AI Series with Seedance 2.5 Prompts — CurieuxExplorer · 2026-08-14
- Midjourney + Seedance 2.5 Combo Sparks Debate on Weekly AI-Animated Shows — gorkem · 2026-08-14
- Developer Builds Offline Universe with MiniMax H3 Requiring Only 5GB VRAM — cocktailpeanut · 2026-08-14
- Major OpenCLIP Update Integrates Audio Models and Variable Resolution — wightmanr · 2026-08-14
- I, Robot Director Alex Proyas Joins Higgsfield AI Film Festival Jury — SimplyAnnisa · 2026-08-14
- HeyGen Integrates Cartesia for Real-Time Conversational AI Avatars — HeyGen · 2026-08-14