SongGeneration v2 large needs about 8.3 GB of memory at Q6_K (a 6.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 6.9 GB (Q6_K) to 7.6 GB (Q8_0).
SongGeneration v2 large is a 5.12B-parameter Songgeneration model in GGUF format, quantized by ngoctham. The repository has 2 quant files, from 6.9 GB (Q6_K) to 7.6 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 6.9 GB | 8.3 GB | Too big | Get file → | |
| Q8_0 | 7.6 GB | 9.0 GB | Too big | Get file → |
What GPU do you need for SongGeneration v2 large?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q8_0 (7.6 GB file, about 9.0 GB in use).
Which SongGeneration v2 large quant should you choose?
Q6_K (6.9 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about SongGeneration v2 large
How much VRAM does SongGeneration v2 large need?
About 8.3 GB at Q6_K with an 8K context window. That is the 6.9 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 SongGeneration v2 large on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of SongGeneration v2 large GGUF?
It depends on the quant: Q6_K is 6.9 GB, Q8_0 is 7.6 GB.
Where can I download SongGeneration v2 large GGUF?
The files are on Hugging Face in the ngoctham/SongGeneration-v2-large-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 SongGeneration v2 large use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.