GR

grug 3b qat q4

GrugGGUF by ProCreationsUpdated 2026-07-26
Download on Hugging Face
Parameters4.17B
Context256K
Layers22
Architecturenanbeige
Smallest quant2.6 GB
Quick answer

grug 3b qat q4 needs about 3.8 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 2.6 GB (Q4_K_M) to 8.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.0 GB.

grug 3b qat q4 is a 4.17B-parameter Grug model in GGUF format, quantized by ProCreations. Its trained context length is 256K tokens. The repository has 2 quant files, from 2.6 GB (Q4_K_M) to 8.3 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.6 GB 3.8 GB
Fits Get file →
F168.3 GB 9.6 GB
Too big Get file →

What GPU do you need for grug 3b qat q4?

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 Q4_K_M (2.6 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (2.6 GB file, about 3.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (2.6 GB file, about 3.8 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (8.3 GB file, about 9.6 GB in use).

Which grug 3b qat q4 quant should you choose?

Q4_K_M is the usual starting point for grug 3b qat q4: it balances file size and quality well. Here it is a 2.6 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturenanbeige
Parameters4.17B
Layers22
Trained context262,144 tokens
KV cache (fp16)88 KB per token

Source

Quantized byProCreations
FamilyGrug
Licenseapache-2.0
Downloads (HF)117
Last updated2026-07-26

Frequently asked questions about grug 3b qat q4

How much VRAM does grug 3b qat q4 need?

About 3.8 GB at Q4_K_M with an 8K context window. That is the 2.6 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 grug 3b qat q4 on an 8 GB GPU?

Yes, with Q4_K_M: the 2.6 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of grug 3b qat q4 GGUF?

It depends on the quant: Q4_K_M is 2.6 GB, F16 is 8.3 GB.

What context length does grug 3b qat q4 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 3.0 GB at 32K.

Where can I download grug 3b qat q4 GGUF?

The files are on Hugging Face in the ProCreations/grug-3b-qat-q4-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 grug 3b qat q4 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.

Other GGUFs of grug-3b

Similar models

Browse all →

More from ProCreations

All by ProCreations →

More Grug models

All Grug →

Other small models

All small models →