KR

krea 2

KreaGGUF by gguf-orgUpdated 2026-07-06
Download on Hugging Face
Parameters12.8B
Context—
Layers—
Architecturepig
Smallest quant0.3 GB
Quick answer

krea 2 needs about 5.1 GB of memory at IQ2_S (a 4.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 16 quants, from 0.3 GB (F16) to 7.2 GB.

krea 2 – 12.8B parameter LLM in GGUF format

krea 2 is a 12.8 billion parameter language model based on the pig architecture. It is available in multiple GGUF quantizations ranging from F16 to IQ4_XS. The model is released under an other license and has no specified language or vision capabilities.

Good at

  • Large language generation
  • Flexible quantization options
  • Compatible with llama.cpp and ComfyUI

Limits

  • No vision support
  • License not specified
  • No trained context tokens

Best for

  • Text generation tasks
  • Fine‑tuning experiments
  • ComfyUI diffusion workflows

Who it’s for. Developers and researchers who need a versatile 12.8B model with a variety of quantization choices. Suitable for local inference on systems with moderate GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.3 GB 0.8 GB
Fits Get file →
IQ1_S2.5 GB 3.3 GB
Fits Get file →
IQ1_M2.8 GB 3.6 GB
Fits Get file →
IQ4_XS3.1 GB 4.0 GB
Fits Get file →
—3.2 GB 4.1 GB
Fits Get file →
IQ2_XXS3.3 GB 4.2 GB
Fits Get file →
IQ2_XS3.7 GB 4.7 GB
Fits Get file →
IQ2_S4.1 GB 5.1 GB
Fits Get file →
Q2_K4.2 GB 5.2 GB
Fits Get file →
Q2_K4.2 GB 5.2 GB
Fits Get file →
IQ3_XXS4.9 GB 6.0 GB
Fits Get file →
IQ3_S5.5 GB 6.7 GB
Fits Get file →
Q3_K_S5.5 GB 6.7 GB
Fits Get file →
IQ4_XS6.8 GB 8.1 GB
Too big Get file →
MXFP4_MOE6.8 GB 8.2 GB
Too big Get file →
—7.2 GB 8.6 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (est. 3.3 GB) or IQ1_M (est. 3.6 GB). If you have 12 GB VRAM, IQ2_S (est. 5.1 GB) or Q2_K (est. 5.2 GB) are good choices. For larger GPUs, IQ4_XS (est. 8.1 GB) or MXFP4_MOE (est. 8.2 GB) provide higher quality.

What GPU do you need for krea 2?

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: the best quant that fits is IQ4_XS (3.1 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ3_XXS (4.9 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_S (5.5 GB file, about 6.7 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (7.2 GB file, about 8.6 GB in use).

Which krea 2 quant should you choose?

IQ2_S (4.1 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

If memory is tight, the smallest file is F16 at 0.3 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

Architecturepig
Parameters12.8B

Source

Quantized bygguf-org
FamilyKrea
Base modelkrea/Krea-2-Raw
Licenseother
Downloads (HF)18,491
Last updated2026-07-06

Frequently asked questions about krea 2

How much VRAM does krea 2 need?

About 5.1 GB at IQ2_S with an 8K context window. That is the 4.1 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 krea 2 on an 8 GB GPU?

Yes, with Q3_K_S: the 5.5 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of krea 2 GGUF?

It depends on the quant: F16 is 0.3 GB, IQ1_S is 2.5 GB, IQ1_M is 2.8 GB, IQ4_XS is 3.1 GB, file is 3.2 GB, IQ2_XXS is 3.3 GB and 10 more.

Where can I download krea 2 GGUF?

The files are on Hugging Face in the gguf-org/krea-2-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 krea 2 use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run krea 2 on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations, which estimate 3.3 GB or 3.6 GB memory at 8k context.

Does krea 2 support vision tasks?

No, the model has no vision capabilities.

What quantization gives the best quality?

Higher precision quantizations like IQ4_XS or MXFP4_MOE offer better quality but require more memory.

Other GGUFs of Krea-2-Raw

Similar models

Browse all →

More from gguf-org

All by gguf-org →

More Krea models

All Krea →

Other medium models

All medium models →