Minimax Music3 needs about 6.1 GB of memory at BF16 (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 7 quants, from 1.5 GB (Q4_0) to 9.6 GB (Q8_0).
MiniMax Music 3 – a 2.46B parameter music generation model
MiniMax Music 3 is a 2.46B parameter model designed for music generation. It can synthesize complete, structurally coherent songs up to 5 minutes long at 32 kHz stereo. The model accepts lyrics and structured music descriptions as conditioning inputs.
Good at
- Generating full-length songs
- Supporting structured section tags
- Accepting detailed music descriptions
Limits
- No vision support
- Requires 8k context for estimates
- License: creativeml-openrail-m
Best for
- Music production workflows
- ComfyUI integration
- Creative songwriting
Who it’s for. Developers and musicians who need a lightweight music generation model that can be run locally. The model is suitable for integration into creative pipelines and for users who prefer open-source solutions.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 1.5 GB | 2.2 GB | Fits | Get file → | |
| — | 2.6 GB | 3.4 GB | Fits | Get file → | |
| Q8_0 | 2.7 GB | 3.5 GB | Fits | Get file → | |
| BF16 | 5.0 GB | 6.1 GB | Fits | Get file → | |
| Q4_0 | 5.8 GB | 7.0 GB | Fits | Get file → | |
| — | 9.1 GB | 10.7 GB | Too big | Get file → | |
| Q8_0 | 9.6 GB | 11.2 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_0 quant (1.49 GB file, 2.2 GB memory). For 12 GB VRAM, the Q8_0 quant (2.7 GB file, 3.5 GB memory) is suitable. If more memory is available, the BF16 quant (4.98 GB file, 6.1 GB memory) offers higher precision.
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 Q4_0 (5.8 GB file, about 7.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.6 GB file, about 11.2 GB in use).
Which Minimax Music3 quant should you choose?
BF16 (5.0 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is Q4_0 at 1.5 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
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 6.1 GB at BF16 with an 8K context window. That is the 5.0 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 Q4_0: the 5.8 GB file needs about 7.0 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: Q4_0 is 1.5 GB, file is 2.6 GB, Q8_0 is 2.7 GB, BF16 is 5.0 GB, Q4_0 is 5.8 GB, file is 9.1 GB and 1 more.
Where can I download Minimax Music3 GGUF?
The files are on Hugging Face in the molbal/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 creativeml-openrail-m. 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 Music 3 on 8 GB VRAM?
Yes, the Q4_0 quant file is 1.49 GB and requires about 2.2 GB of VRAM at 8k context.
Does MiniMax Music 3 support image conditioning?
No, the model does not support vision or image inputs.
What license applies to this model?
The model is released under the creativeml-openrail-m license.