covasna 0.1 imatrix needs about 24.4 GB of memory at its main file (a 22.2 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 6 quants, from 14.1 GB to 44.4 GB.
covasna 0.1 imatrix is a 41.6B-parameter Covasna model in GGUF format, quantized by nisten. Its trained context length is 32K tokens. The repository has 6 quant files, from 14.1 GB to 44.4 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 14.1 GB | 16.2 GB | Too big | Get file → | |
| — | 18.0 GB | 20.1 GB | Too big | Get file → | |
| — | 22.2 GB | 24.4 GB | Too big | Get file → | |
| — | 29.4 GB | 31.5 GB | Too big | Get file → | |
| — | 34.1 GB | 36.2 GB | Too big | Get file → | |
| — | 44.4 GB | 46.6 GB | Too big | Get file → |
What GPU do you need for covasna 0.1 imatrix?
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: the best quant that fits is the main file (18.0 GB file, about 20.1 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (29.4 GB file, about 31.5 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (44.4 GB file, about 46.6 GB in use).
Which covasna 0.1 imatrix quant should you choose?
If memory is tight, the smallest file is the first one in the table at 14.1 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 covasna 0.1 imatrix
How much VRAM does covasna 0.1 imatrix need?
About 24.4 GB at its main file with an 8K context window. That is the 22.2 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 covasna 0.1 imatrix on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of covasna 0.1 imatrix GGUF?
It depends on the quant: file is 14.1 GB, file is 18.0 GB, file is 22.2 GB, file is 29.4 GB, file is 34.1 GB, file is 44.4 GB.
What context length does covasna 0.1 imatrix support?
The GGUF header lists a trained context length of 32,764 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download covasna 0.1 imatrix GGUF?
The files are on Hugging Face in the nisten/covasna-0.1-imatrix-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 covasna 0.1 imatrix 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.