UNET needs about 14.7 GB of memory at Q8_0 (a 12.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 5 quants, from 6.8 GB (Q4_K_S) to 15.4 GB (Q8_0).
UNET is a 11.9B-parameter Unet model in GGUF format, quantized by f5aiteam. The repository has 5 quant files, from 6.8 GB (Q4_K_S) to 15.4 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_S | 6.8 GB | 8.1 GB | Too big | Get file → | |
| Q6_K | 9.9 GB | 11.5 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 14.7 GB | Too big | Get file → | |
| Q8_0 | 15.4 GB | 17.8 GB | Too big | Get file → | |
| Q8_0 | 15.4 GB | 17.8 GB | Too big | Get file → |
What GPU do you need for UNET?
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 Q6_K (9.9 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 14.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (15.4 GB file, about 17.8 GB in use).
Which UNET quant should you choose?
Q8_0 (12.7 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 Q4_K_S at 6.8 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
Frequently asked questions about UNET
How much VRAM does UNET need?
About 14.7 GB at Q8_0 with an 8K context window. That is the 12.7 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 UNET on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of UNET GGUF?
It depends on the quant: Q4_K_S is 6.8 GB, Q6_K is 9.9 GB, Q8_0 is 12.7 GB, Q8_0 is 15.4 GB, Q8_0 is 15.4 GB.
Where can I download UNET GGUF?
The files are on Hugging Face in the f5aiteam/UNET repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.