molbal / text-to-image updated 1 week ago

krea2-gguf

Name: krea2-gguf
Author: molbal

--- license: other licensename: krea-2-community-license licenselink: https://huggingface.co/krea/Krea-2-Turbo/blob/main/LICENSE pipelinetag: text-to-image tags: - image-generation - diffusion - flow-matching - dit - krea2 - quantization - comfyui libraryname: gguf basemodel: - krea/Krea-2-Raw - krea/Krea-2-Turbo ---

Params

—

Context

—

Downloads 30d

17 K

Likes

Licence: other Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 10 days

19 K17 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
krea2_raw_bf16-Q4_0.gguf	Q4_0	8.3 GB	9.6 GB	✅ Runs comfortably
krea2_raw_bf16-Q4_1.gguf	Q4_1	9.1 GB	10.5 GB	✅ Runs comfortably
krea2_raw_bf16-Q5_0.gguf	Q5_0	9.9 GB	11.4 GB	✅ Runs comfortably
krea2_raw_bf16-Q5_1.gguf	Q5_1	10.7 GB	12.2 GB	✅ Runs comfortably
krea2_turbo_bf16-Q8_CR.gguf	Q8_CR	13.8 GB	15.7 GB	✅ Runs comfortably
krea2_raw_bf16-Q8_0.gguf	Q8_0	14.6 GB	16.5 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Licence: other
First seen on the Hub: 2026-06-24
Base model: Krea-2-Raw
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base Krea-2-Raw krea 133 K

Compare with

stable-diffusion-v1-5 1.6 M stable-diffusion-xl-base-1.0 1.5 M sdxl-turbo 1.1 M Z-Image-Turbo 1.1 M dreamshaper-7 895 K Flux2-Klein-9B-True-V2 792 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB