AG

agata

AgataGGUF by unlovedUpdated 2025-04-28
Download on Hugging Face
Parameters3.09B
Context125K
Layers36
Architectureqwen2vl
Smallest quant3.3 GB
Quick answer

agata needs about 4.1 GB of memory at Q8_0 (a 3.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 3.3 GB (Q8_0) to 6.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

agata is a 3.09B-parameter Agata model in GGUF format, quantized by unloved. Its trained context length is 125K tokens. The repository has 2 quant files, from 3.3 GB (Q8_0) to 6.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_03.3 GB 4.1 GB
Fits Get file →
F166.2 GB 7.0 GB
Fits Get file →

What GPU do you need for agata?

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: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.2 GB file, about 7.0 GB in use).

Which agata quant should you choose?

Q8_0 (3.3 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2vl
Parameters3.09B
Layers36
Trained context128,000 tokens
KV cache (fp16)36 KB per token

Source

Quantized byunloved
FamilyAgata
Repositoryunloved/agata
Downloads (HF)16
Last updated2025-04-28

Frequently asked questions about agata

How much VRAM does agata need?

About 4.1 GB at Q8_0 with an 8K context window. That is the 3.3 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 agata on an 8 GB GPU?

Yes, with F16: the 6.2 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of agata GGUF?

It depends on the quant: Q8_0 is 3.3 GB, F16 is 6.2 GB.

What context length does agata support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.

Where can I download agata GGUF?

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

Similar models

Browse all →

More from unloved

All by unloved →

Other tiny models

All tiny models →