MusicGen needs about 1.4 GB of memory at Q8_0 (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.3 GB (BF16) to 4.5 GB (Q8_0).
MusicGen is a 4.19B-parameter Musicgen model in GGUF format, quantized by CreativeHub008. Its trained context length is 40K tokens. The repository has 4 quant files, from 0.3 GB (BF16) to 4.5 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q8_0 | 0.8 GB | 1.4 GB | Fits | Get file → | |
| Q8_0 | 2.5 GB | 3.4 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 5.5 GB | Fits | Get file → |
What GPU do you need for MusicGen?
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 (2.5 GB file, about 3.4 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 5.5 GB in use).
Which MusicGen quant should you choose?
Q8_0 (0.8 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is BF16 at 0.3 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MusicGen
How much VRAM does MusicGen need?
About 1.4 GB at Q8_0 with an 8K context window. That is the 0.8 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 MusicGen on an 8 GB GPU?
Yes, with Q8_0: the 4.5 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MusicGen GGUF?
It depends on the quant: BF16 is 0.3 GB, Q8_0 is 0.8 GB, Q8_0 is 2.5 GB, Q8_0 is 4.5 GB.
What context length does MusicGen support?
The GGUF header lists a trained context length of 40,960 tokens (40K).
Where can I download MusicGen GGUF?
The files are on Hugging Face in the CreativeHub008/MusicGen repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.