Vikras 12 to 18b collection needs about 10.8 GB of memory at MXFP4 (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 8.7 GB (Q6_K) to 9.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Vikras 12 to 18b collection is a 12.2B-parameter Vikras model in GGUF format, quantized by srs6901. Its trained context length is 1000K tokens. The repository has 3 quant files, from 8.7 GB (Q6_K) to 9.4 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 8.7 GB | 10.6 GB | Too big | Get file → | |
| MXFP4 | 9.0 GB | 10.8 GB | Too big | Get file → | |
| — | 9.4 GB | 11.2 GB | Too big | Get file → |
What GPU do you need for Vikras 12 to 18b collection?
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: the best quant that fits is the main file (9.4 GB file, about 11.2 GB in use).
Which Vikras 12 to 18b collection quant should you choose?
MXFP4 (9.0 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
If memory is tight, the smallest file is Q6_K at 8.7 GB, with the quality trade-offs that come with fewer bits. 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 Vikras 12 to 18b collection
How much VRAM does Vikras 12 to 18b collection need?
About 10.8 GB at MXFP4 with an 8K context window. That is the 9.0 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 Vikras 12 to 18b collection on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Vikras 12 to 18b collection GGUF?
It depends on the quant: Q6_K is 8.7 GB, MXFP4 is 9.0 GB, file is 9.4 GB.
What context length does Vikras 12 to 18b collection support?
The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Vikras 12 to 18b collection GGUF?
The files are on Hugging Face in the srs6901/Vikras-12-to-18b-collection repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Vikras 12 to 18b collection 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.