MiniMax Music3 needs about 2.2 GB of memory at Q4_K_M (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 1.2 GB (Q3_K_M) to 5.0 GB (F16).
MiniMax Music3 – a 2.46B parameter text‑to‑music model that generates full songs up to five minutes.
MiniMax Music3 is a 2.46B parameter model that produces 32 kHz, 16‑bit stereo WAV audio. It accepts lyrics with section tags and a detailed music description to create structurally coherent songs. The model uses a hierarchical autoregressive architecture with an 8B global LLM and a 0.6B local LLM.
Good at
- Full‑song generation up to five minutes
- Fine‑grained control via lyrics and music description
- Stable long‑form audio quality
Limits
- No vision support
- Requires companion text encoder and VAE
- Large VRAM for higher quantizations
Best for
- Music production workflows
- Creative songwriting tools
- Audio research projects
Who it’s for. The model is suited for musicians, producers, and researchers who need high‑quality, controllable music generation. It is also useful for developers building music‑generation applications with ComfyUI.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 1.2 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_M | 1.5 GB | 2.2 GB | Fits | Get file → | |
| Q5_K_M | 1.8 GB | 2.5 GB | Fits | Get file → | |
| Q6_K | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q8_0 | 2.7 GB | 3.5 GB | Fits | Get file → | |
| F16 | 5.0 GB | 6.1 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.49 GB file, 2.2 GB memory). For 12 GB VRAM, Q5_K_M (1.79 GB file, 2.5 GB memory). For 16 GB VRAM, Q6_K (2.12 GB file, 2.9 GB memory). Higher quantizations increase VRAM usage.
What GPU do you need for MiniMax Music3?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q8_0 (2.7 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (2.7 GB file, about 3.5 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (5.0 GB file, about 6.1 GB in use).
Which MiniMax Music3 quant should you choose?
Q4_K_M is the usual starting point for MiniMax Music3: it balances file size and quality well. Here it is a 1.5 GB file.
The Q8_0 file is 2.7 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q3_K_M at 1.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MiniMax Music3
How much VRAM does MiniMax Music3 need?
About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run MiniMax Music3 on an 8 GB GPU?
Yes, with F16: the 5.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiniMax Music3 GGUF?
It depends on the quant: Q3_K_M is 1.2 GB, Q4_K_M is 1.5 GB, Q5_K_M is 1.8 GB, Q6_K is 2.1 GB, Q8_0 is 2.7 GB, F16 is 5.0 GB.
Where can I download MiniMax Music3 GGUF?
The files are on Hugging Face in the Abiray/MiniMax-Music3-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does MiniMax Music3 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run MiniMax Music3 on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 2.2 GB VRAM at 8k context.
Do I need additional models to generate music?
Yes, the GGUF file replaces only the diffusion transformer. A text encoder and VAE are required.
What license applies to this model?
The model is released under the Apache‑2.0 license.