Kopernikus guff needs about 69.0 GB of memory at Q6_K (a 65.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 65.8 GB (Q6_K) to 145.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Kopernikus guff is a 72.7B-parameter Kopernikus model in GGUF format, quantized by Toramannnn. Its trained context length is 128K tokens. The repository has 2 quant files, from 65.8 GB (Q6_K) to 145.4 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 65.8 GB | 69.0 GB | Too big | Get file → | |
| — | 145.4 GB | 148.6 GB | Too big | Get file → |
What GPU do you need for Kopernikus guff?
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: 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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Kopernikus guff quant should you choose?
Q6_K (65.8 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 Kopernikus guff
How much VRAM does Kopernikus guff need?
About 69.0 GB at Q6_K with an 8K context window. That is the 65.8 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 Kopernikus guff on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 69.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Kopernikus guff GGUF?
It depends on the quant: Q6_K is 65.8 GB, file is 145.4 GB.
What context length does Kopernikus guff support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download Kopernikus guff GGUF?
The files are on Hugging Face in the Toramannnn/Kopernikus-guff repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Kopernikus guff use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.