Model reference · open weights
Minimax-Music3 is an open-weight audio or speech model from molbal, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
MiniMax Music 3 - GGUF Quantizations This repository contains GGUF quantizations for MiniMax Music 3 (Hugging Face model), a music generation model capable of synthesizing complete, structurally coherent songs up to 5 minutes long at 32 kHz stereo. For full architectural details, model specifications, and benchmarks, please refer to the official MiniMax-Music3 GitHub repository. Example Workflow An example ComfyUI workflow is included in the examples/ directory: examples/minimax-music-3.json Quantized Models Diffusion Transformer (Flow Matching 2.4B DiT) Place these files in ComfyUI/models/diffusionmodels/ or ComfyUI/models/unet/: Pruned Text & Language Model Encoder Place these files in ComfyUI/models/textencoders/ or ComfyUI/models/clip/: ComfyUI Node Requirements To load and generate music with these GGUF weights in ComfyUI: 1. ComfyUI-GGUF: Repository: molbal/ComfyUI-GGUF Registry: comfyui-gguf-reboot 2. Load the workflow provided at examples/minimax-music-3.json. Prompting Guide MiniMax Music 3 accepts two primary conditioning inputs: Lyrics and a Music Description. 1. Lyrics & Section Tags Structure your lyrics using standard uppercase section tags placed on their own lines: Supported section tags include: [Intro], [Verse], [Pre-Chorus], [Chorus], [Post-Chorus], [Bridge], [Instrumental], [Solo], and [Outro]. 2. Structured Caption (Music Description) For precise control over the arrangement and performance, structure your music description across three areas: Global Metadata: Genre, subgenre, tempo (BPM), key, scale, emotional progression, listening scenario, and production style. Vocal Details: Vocal gender, timbre, performance delivery, harmony, backing vocals, and vocal effects (e.g. reverb, delay). Arrangement: Primary and secondary instruments, section-by-section instrument progression, groove/rhythm, bassline, percussion style, and spatial atmosphere. Example Structured Caption: Limitations Generation is non-streaming. The tokenized text prompt is limited to 5,000 tokens. Audio generation is capped at 9,000 acoustic frames (~5 minutes). Section tags and descriptions provide generative conditioning; tempo, key, and lyrical timing may vary slightly. Ori
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | molbal |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Released | 2026-08-13 |
| Popularity | 17k downloads / month |
| Likes | 1 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| Minimax-Music3-GGUF | — | GGUF | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys molbal-minimax-music3 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (molbal-minimax-music3 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="molbal-minimax-music3" -F file=@audio.mp3
Details
Tags
Licence
Open weights under creativeml-openrail-m — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗