SD needs about 11.3 GB of memory at its main file (a 9.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 9.7 GB to 9.7 GB.
SD is a 14.3B-parameter Tppp model in GGUF format, quantized by tppp2806. The repository has 2 quant files, from 9.7 GB to 9.7 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 9.7 GB | 11.3 GB | Too big | Get file → | |
| — | 9.7 GB | 11.3 GB | Too big | Get file → |
What GPU do you need for SD?
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 the main file (9.7 GB file, about 11.3 GB in use).
Specifications
Architecture from the GGUF header
Frequently asked questions about SD
How much VRAM does SD need?
About 11.3 GB at its main file with an 8K context window. That is the 9.7 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 SD on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of SD GGUF?
It depends on the quant: file is 9.7 GB, file is 9.7 GB.
Where can I download SD GGUF?
The files are on Hugging Face in the tppp2806/SD repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.