GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

gguf-org/krea-2-gguf overview

krea 2 gguf drag pig to ./ComfyUI/models/vae drag qwen3vl 4b to ./ComfyUI/models/text encoders compatible with this https://huggingface.co/Qwen/Qwen3 VL 4B Ins…

ggufbase_model:krea/Krea-2-Rawbase_model:quantized:krea/Krea-2-Rawlicense:otherregion:us

Runs locally from ~242.1 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
3,746
Likes
8
Pipeline
Author

Repository Files & Downloads

16 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
krea2_raw-q2_k.ggufGGUFQ2_K3.92 GBDownload
krea2_turbo-iq1_m.ggufGGUFIQ1_M2.62 GBDownload
krea2_turbo-iq1_s.ggufGGUFIQ1_S2.34 GBDownload
krea2_turbo-iq2_s.ggufGGUFIQ2_S3.83 GBDownload
krea2_turbo-iq2_xs.ggufGGUFIQ2_XS3.46 GBDownload
krea2_turbo-iq2_xxs.ggufGGUFIQ2_XXS3.08 GBDownload
krea2_turbo-iq3_s.ggufGGUFIQ3_S5.14 GBDownload
krea2_turbo-iq3_xxs.ggufGGUFIQ3_XXS4.58 GBDownload
krea2_turbo-iq4_xs.ggufGGUFIQ4_XS6.35 GBDownload
krea2_turbo-mxfp4_moe.ggufGGUFGGUF6.37 GBDownload
krea2_turbo-nvfp4.ggufGGUFGGUF6.72 GBDownload
krea2_turbo-q2_k.ggufGGUFQ2_K3.92 GBDownload
krea2_turbo-q3_k_s.ggufGGUFQ3_K_S5.14 GBDownload
pig_wan_vae_fp32-f16.ggufGGUFF16242.1 MBDownload
qwen3vl_4b-iq4_xs.ggufGGUFIQ4_XS2.88 GBDownload
qwen3vl_4b-nvfp4.ggufGGUFGGUF3.00 GBDownload

Model Details

Model IDgguf-org/krea-2-gguf
Authorgguf-org
Pipeline
Licenseother
Base modelkrea/Krea-2-Raw
Last modified2026-07-06T03:13:27.000Z

Model README

---

license: other

license_name: krea-2-community-license

license_link: https://huggingface.co/krea/Krea-2-Turbo/blob/main/LICENSE.pdf

base_model:

  • krea/Krea-2-Raw

widget:

  • text: >-

cute anime style girl with massive fluffy fennec ears and a big fluffy tail

blonde messy long hair blue eyes wearing a maid outfit with a long black

gold leaf pattern dress and a white apron, it is a postcard held by a hand

in front of a beautiful realistic city at sunset and there is cursive

writing that says "Now in GGUF"

output:

url: workflow-demo-01.png

  • text: >-

A crystal dragon soaring through an aurora borealis sky, its entire body

made of transparent faceted crystal refracting the green and purple aurora

light into rainbow spectra, ice particles trailing from its wings, high

fantasy digital art

output:

url: workflow-demo-02.png

  • text: >-

A crystal phoenix soaring through an aurora borealis sky, its entire body

made of transparent faceted crystal refracting the green and purple aurora

light into rainbow spectra, ice particles trailing from its wings, high

fantasy digital art

output:

url: workflow-demo-03.png

  • text: >-

iq2_s (same prompt as 1st one)

output:

url: workflow-iq2_s.png

  • text: >-

iq2_xs (same prompt as 1st one)

output:

url: workflow-iq2_xs.png

  • text: >-

iq3_xxs (same prompt as 1st one)

output:

url: workflow-iq3_xxs.png

  • text: >-

mxfp4 (same prompt as 1st one)

output:

url: workflow-mxfp4-test.png

  • text: >-

nvfp4 (same prompt as 1st one)

output:

url: workflow-nvfp4-test.png

  • text: >-

nvfp4 (model) + nvfp4 (clip)

output:

url: workflow-demo-04.png

---

krea-2-gguf

  • drag pig to > ./ComfyUI/models/vae
  • drag qwen3vl-4b to > ./ComfyUI/models/text_encoders

- compatible with this, this, this, etc. (but 🐷 reversible, opt anyone you like)

  • drag krea2 to > ./ComfyUI/models/diffusion_models

!screenshot

<Gallery />

compatible with gguf-desktop or stable-diffusion.cpp

!screenshot

note: feel free to test nvfp4 and mxfp4 on gguf node and/or gguf-desktop ⚽🐖 *btw, you could make all the other quant types yourself with Quant tab from gguf-desktop and test it one by one; enjoy your long weekend

Run gguf-org/krea-2-gguf with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models