KR

krea2

KreaGGUF by rectanglewormUpdated 2026-09-05
Download on Hugging Face
Parameters12.8B
Context—
Layers—
Architecturekrea2
Smallest quant7.2 GB
Quick answer

krea2 needs about 8.6 GB of memory at Q4_K_M (a 7.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 7.2 GB (Q4_K) to 8.3 GB (Q4_K_S).

krea2 is a 12.8B-parameter Krea model in GGUF format, quantized by rectangleworm. The repository has 5 quant files, from 7.2 GB (Q4_K) to 8.3 GB (Q4_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K7.2 GB 8.6 GB
Too big Get file →
Q4_K7.2 GB 8.6 GB
Too big Get file →
Q4_K7.2 GB 8.6 GB
Too big Get file →
Q4_K_M7.2 GB 8.6 GB
Too big Get file →
Q4_K_S8.3 GB 9.8 GB
Too big Get file →

What GPU do you need for krea2?

These figures add the file size, an fp16 KV cache at an 8K context window 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 Q4_K_S (8.3 GB file, about 9.8 GB in use).

Which krea2 quant should you choose?

Q4_K_M is the usual starting point for krea2: it balances file size and quality well. Here it is a 7.2 GB file.

If memory is tight, the smallest file is Q4_K at 7.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturekrea2
Parameters12.8B

Source

Quantized byrectangleworm
FamilyKrea
Downloads (HF)788
Last updated2026-09-05

Frequently asked questions about krea2

How much VRAM does krea2 need?

About 8.6 GB at Q4_K_M with an 8K context window. That is the 7.2 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 krea2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of krea2 GGUF?

It depends on the quant: Q4_K is 7.2 GB, Q4_K is 7.2 GB, Q4_K is 7.2 GB, Q4_K_M is 7.2 GB, Q4_K_S is 8.3 GB.

Where can I download krea2 GGUF?

The files are on Hugging Face in the rectangleworm/krea2-gguf 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 rectangleworm

All by rectangleworm →

More Krea models

All Krea →

Other medium models

All medium models →