music needs about 4.6 GB of memory at Q4_K_M (a 3.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 17 quants, from 0.3 GB (BF16) to 10.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
music is a 596M-parameter Music model in GGUF format, quantized by zw89. Its trained context length is 32K tokens. The repository has 17 quant files, from 0.3 GB (BF16) to 10.0 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 0.3 GB | 1.9 GB | Fits | Get file → | |
| Q8_0 | 0.8 GB | 2.4 GB | Fits | Get file → | |
| BF16 | 1.2 GB | 2.8 GB | Fits | Get file → | |
| BF16 | 1.3 GB | 2.9 GB | Fits | Get file → | |
| Q8_0 | 2.0 GB | 3.5 GB | Fits | Get file → | |
| Q8_0 | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_M | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q4_K_M | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q6_K | 3.4 GB | 5.0 GB | Fits | Get file → | |
| BF16 | 3.7 GB | 5.3 GB | Fits | Get file → | |
| Q6_K | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 6.0 GB | Fits | Get file → | |
| BF16 | 4.8 GB | 6.4 GB | Fits | Get file → | |
| Q8_0 | 5.3 GB | 6.9 GB | Fits | Get file → | |
| Q8_0 | 5.3 GB | 6.9 GB | Fits | Get file → | |
| BF16 | 8.4 GB | 10.0 GB | Too big | Get file → | |
| — | 10.0 GB | 11.6 GB | Too big | Get file → |
What GPU do you need for music?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 (2.0 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.3 GB file, about 6.9 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (10.0 GB file, about 11.6 GB in use).
Which music quant should you choose?
Q4_K_M is the usual starting point for music: it balances file size and quality well. Here it is a 3.0 GB file.
The Q8_0 file is 0.8 GB, about 0.3 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 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
Frequently asked questions about music
How much VRAM does music need?
About 4.6 GB at Q4_K_M with an 8K context window. That is the 3.0 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 music on an 8 GB GPU?
Yes, with Q8_0: the 5.3 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of music GGUF?
It depends on the quant: BF16 is 0.3 GB, Q8_0 is 0.8 GB, BF16 is 1.2 GB, BF16 is 1.3 GB, Q8_0 is 2.0 GB, Q8_0 is 2.5 GB and 11 more.
What context length does music support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download music GGUF?
The files are on Hugging Face in the zw89/music repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.