VA

vas models

VasGGUF by VisualArchiveSystemUpdated 2026-04-09
Download on Hugging Face
Parameters3.88B
Context128K
Layers34
Architecturegemma3
Smallest quant0.7 GB
Quick answer

vas models needs about 4.1 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 0.7 GB (F16) to 4.7 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.

vas models is a 3.88B-parameter Vas model in GGUF format, quantized by VisualArchiveSystem. Its trained context length is 128K tokens. The repository has 4 quant files, from 0.7 GB (F16) to 4.7 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.7 GB 2.3 GB
Fits Get file →
Q4_K_M2.5 GB 4.1 GB
Fits Get file →
Q4_K_M2.5 GB 4.1 GB
Fits Get file →
Q4_K_M4.7 GB 6.3 GB
Fits Get file →

What GPU do you need for vas models?

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: the best quant that fits is F16 (0.7 GB file, about 2.3 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (2.5 GB file, about 4.1 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 6.3 GB in use).

Which vas models quant should you choose?

Q4_K_M is the usual starting point for vas models: it balances file size and quality well. Here it is a 2.5 GB file.

If memory is tight, the smallest file is F16 at 0.7 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters3.88B
Layers34
Trained context131,072 tokens
KV cache (fp16)136 KB per token

Source

FamilyVas
Licenseapache-2.0
Downloads (HF)57
Last updated2026-04-09

Frequently asked questions about vas models

How much VRAM does vas models need?

About 4.1 GB at Q4_K_M with an 8K context window. That is the 2.5 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 vas models on an 8 GB GPU?

Yes, with Q4_K_M: the 4.7 GB file needs about 6.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of vas models GGUF?

It depends on the quant: F16 is 0.7 GB, Q4_K_M is 2.5 GB, Q4_K_M is 2.5 GB, Q4_K_M is 4.7 GB.

What context length does vas models support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.

Where can I download vas models GGUF?

The files are on Hugging Face in the VisualArchiveSystem/vas-models repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does vas models 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.

Similar models

Browse all →

More Vas models

All Vas →

Other small models

All small models →