zelensky 78b needs about 62.5 GB of memory at its main file (a 59.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 43.5 GB to 153.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 11.5 GB.
zelensky 78b is a 78B-parameter Zelensky model in GGUF format, quantized by nisten. Its trained context length is 96K tokens. The repository has 7 quant files, from 43.5 GB to 153.6 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 43.5 GB | 46.9 GB | Too big | Get file → | |
| — | 45.2 GB | 48.6 GB | Too big | Get file → | |
| — | 51.6 GB (2 parts) | 55.0 GB | Too big | Get file → | |
| — | 59.1 GB (2 parts) | 62.5 GB | Too big | Get file → | |
| — | 69.6 GB (2 parts) | 73.0 GB | Too big | Get file → | |
| — | 82.9 GB (2 parts) | 86.2 GB | Too big | Get file → | |
| F16 | 153.6 GB (4 parts) | 157.0 GB | Too big | Get file → |
What GPU do you need for zelensky 78b?
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: the best quant that fits is the main file (43.5 GB file, about 46.9 GB in use).
Which zelensky 78b quant should you choose?
If memory is tight, the smallest file is the first one in the table at 43.5 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about zelensky 78b
How much VRAM does zelensky 78b need?
About 62.5 GB at its main file with an 8K context window. That is the 59.1 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 zelensky 78b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 46.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of zelensky 78b GGUF?
It depends on the quant: file is 43.5 GB, file is 45.2 GB, file is 51.6 GB, file is 59.1 GB, file is 69.6 GB, file is 82.9 GB and 1 more.
What context length does zelensky 78b support?
The GGUF header lists a trained context length of 98,304 tokens (96K). The KV cache grows with the context you use: about 2.9 GB at 8K and 11.5 GB at 32K.
Where can I download zelensky 78b GGUF?
The files are on Hugging Face in the nisten/zelensky-78b-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 zelensky 78b 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.