MiniMax Open-Sources Music 3, Generating 5-Minute Full Songs

MiniMax has officially released and open-sourced its Music 3 generation model, making the weights available on Hugging Face for users to download and try.

Confirmed

Model Architecture: Combines an 8B parameter LLM with a 2.7B parameter DiT architecture.
Generation Capabilities: Capable of generating complete songs up to 5 minutes long based on input prompts and lyrics, featuring long-term structural coherence, expressive vocals, and evolving arrangements.
Ecosystem Compatibility: The model is integrated with 🧨 Diffusers and ComfyUI, and supports running on consumer-grade GPUs, significantly lowering the hardware barrier for local deployment.

Timeline

08-13: Developers discovered a PR for this model in the Hugging Face Diffusers library, with the official team submitting multiple generated samples for preview.
08-14: Comfy-Org published the model on Hugging Face, followed by the official announcement of the open-source release and weight availability.

Why It Matters

MiniMax Music 3 claims to achieve SOTA-level song generation capabilities. Its consumer-friendly GPU support offers a highly promising local audio generation tool for developers, creators, and the open-source community.

2026-08-13 ~ 2026-08-14 · 13 related posts

Primary sources

MiniMax-Music3 Hits Top of Hugging Face Trending for Audio Generation — MiniMaxAI · 2026-08-14 01:17 (UTC+08:00)
MiniMax Releases Music 3: Generating Up to 5-Minute Complete Songs — PurzBeats · 2026-08-14 00:28 (UTC+08:00)
MiniMax Music 3 Released with Open Weights: Runs on Consumer GPUs — multimodalart · 2026-08-14 00:02 (UTC+08:00)

Minimax Music 3 Open-Weight Release Imminent as Samples Surface — rerri · 2026-08-13
[source] MiniMax Music 3 Released with Open Weights: Runs on Consumer GPUs — multimodalart · 2026-08-14
MiniMax-Music-3 Model Now Available on Hugging Face — LadyQuacklin · 2026-08-14
MiniMax Releases Music3 Generative Model — Sea_Tomatillo1921 · 2026-08-14
MiniMax Launches Music 3: Generates Up to 5-Minute Complete Songs — huggingface · 2026-08-14
MiniMax Launches Music3: Next-Gen Open-Weights Production-Ready Music Model — bennash · 2026-08-14
[source] MiniMax-Music3 Hits Top of Hugging Face Trending for Audio Generation — MiniMaxAI · 2026-08-14
MiniMax Releases Open-Weights Music Model Music 3, Gets Day 0 Support from SGLang — ying11231 · 2026-08-14

5 near-duplicate retellings: multimodalart · PurzBeats · multimodalart · BanghuaZ · Acceptable-Cycle4645