VA

VAETKI

VaetkiGGUF by dororodoroddoUpdated 2026-01-15
Download on Hugging Face
Parameters112B
Context128K
Layers48
Architecturevaetki
Smallest quant67.7 GB
Quick answer

VAETKI needs about 74.3 GB of memory at Q4_K_M (a 67.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 67.7 GB (Q4_K_M) to 224.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 24.2 GB.

VAETKI is a 112B-parameter Vaetki model in GGUF format, quantized by dororodoroddo. Its trained context length is 128K tokens. The repository has 2 quant files, from 67.7 GB (Q4_K_M) to 224.4 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M67.7 GB 74.3 GB
Too big Get file →
F16224.4 GB 231.0 GB
Too big Get file →

What GPU do you need for VAETKI?

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 VAETKI quant should you choose?

Q4_K_M is the usual starting point for VAETKI: it balances file size and quality well. Here it is a 67.7 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturevaetki
Parameters112B (approximate, mixture of experts)
Layers48
Trained context131,072 tokens
KV cache (fp16)720 KB per token

Source

Quantized bydororodoroddo
FamilyVaetki
Licensemit
Downloads (HF)41
Last updated2026-01-15

Frequently asked questions about VAETKI

How much VRAM does VAETKI need?

About 74.3 GB at Q4_K_M with an 8K context window. That is the 67.7 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 VAETKI on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 74.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of VAETKI GGUF?

It depends on the quant: Q4_K_M is 67.7 GB, F16 is 224.4 GB.

What context length does VAETKI support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 6.0 GB at 8K and 24.2 GB at 32K.

Where can I download VAETKI GGUF?

The files are on Hugging Face in the dororodoroddo/VAETKI-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 VAETKI 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.

Similar models

Browse all →

More from dororodoroddo

All by dororodoroddo →

More Vaetki models

All Vaetki →

Other large models

All large models →