---
title: "MiniMax Drops Music 3, an Open-Weight AI That Writes 5-Minute Songs"
subtitle: "MiniMax releases an open-weight text-to-music model that generates full 5-minute songs in 32 kHz stereo with native ComfyUI support."
url: "https://alphasignal.ai/news/minimax-drops-music-3-an-open-weight-ai-that-writes-5-minute-songs"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-11-05T15:30:34.971Z"
updated: "2026-11-05T15:33:55.354Z"
type: "Model"
topics:
  - "Audio"
  - "Open Source"
subtopics:
  - "Music Generation"
upvotes: 3882
source_url: "https://huggingface.co/Comfy-Org/MiniMax-Music-3"
comments: 0
truncated: true
---

# MiniMax Drops Music 3, an Open-Weight AI That Writes 5-Minute Songs

> MiniMax releases an open-weight text-to-music model that generates full 5-minute songs in 32 kHz stereo with native ComfyUI support.

MiniMax has released [MiniMax Music 3](https://huggingface.co/MiniMaxAI/MiniMax-Music3), an open-weight model that generates structured songs from section-tagged lyrics and a written description of the sound. It produces up to five minutes of 32 kHz stereo audio, including vocals, instrumentation, and transitions between song sections. The [ComfyUI package](https://huggingface.co/Comfy-Org/MiniMax-Music-3) had passed 950,000 Hugging Face downloads when this article was prepared, although that counter includes file requests rather than unique installations.

Downloadable weights give developers control over deployment, quantization, fine-tuning, and data handling without tying production to a hosted API. Open-weight access still comes with a custom license, hardware costs, and responsibility for operating the generation pipeline.

## The release at a glance

| Capability       | Details                                                                   |
| ---------------- | ------------------------------------------------------------------------- |
| Inputs           | Tagged lyrics and a prose music description                               |
| Maximum duration | Five minutes, with earlier stopping possible                              |
| Audio format     | 32 kHz stereo                                                             |
| Core models      | 8B Global LLM and 0.6B Local LLM                                          |
| Primary runtimes | ComfyUI, Python with Diffusers, and community MLX or GGUF builds          |
| Approximate VRAM | About 22 GB with CPU offloading, or 8 GB with additional group offloading |

## A song stack in four stages

Music 3 uses a hierarchical autoregressive architecture, meaning each new segment depends on earlier segments while separate models work at broad and fine time scales. This division lets the system track a song’s structure across minutes and restore acoustic detail within individual frames.

1. **Global planning:** An 8B Global LLM initialized from Qwen3-8B tracks lyrics, themes, rhythm, vocal identity, and arrangement across the song.
2. **Local detail:** A 0.6B Local LLM models short-range acoustic information within each frame.
3. **Latent synthesis:** A flow-matching transformer converts the language-model states into Flow-VAE latents one chunk at a time.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [MiniMax Music 3 - Hugging Face](https://huggingface.co/MiniMaxAI/MiniMax-Music3)
- [MiniMax Music 3: State of the Art Open Weight Music Generation](https://blog.comfy.org/p/minimax-music-3-state-of-the-art)
- [MiniMax Music 3 - Diffusers docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/minimax_music3)
- [MiniMax Music 3: The Open-Weight AI Music Model, Explained](https://www.mindstudio.ai/blog/minimax-music-3-open-weight)
- [MiniMax-Music3 GGUF Quantizations](https://huggingface.co/Abiray/MiniMax-Music3-GGUF)
