Krea-2-Raw
kreaOthertextvision

Krea-2-Raw

Updated Nov 13, 2026
Parameters
12.8B
Context
8,192
License
Other
Updated
Nov 13, 2026

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at Q8_0
3 of 4 quantizations fit Krea-2-Raw with real runtime overhead.
Q4_K_M
7 GB
Q5_K_M
9 GB
Q8_0
14 GB
FP16
26 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve krea/Krea-2-Raw

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

Krea-2-Raw is an open-weight image generation model from krea, published on Hugging Face in June 2026. It has 12.8B parameters and is released under a custom license (see the model card).

HardwareLink to this section

At full FP16 precision the weights need about 26 GB of memory; 8-bit quantization brings that to roughly 14 GB. Check the VRAM tiers above to see which GPUs fit it.

PopularityLink to this section

Krea-2-Raw had 107,972 downloads on Hugging Face in the last month and has 1,334 likes.

Run it locallyLink to this section

The weights are on Hugging Face and load with Hugging Face Diffusers (or ComfyUI). Follow the model card for the exact setup and license terms.

Frequently asked

Quick answers to common questions

How much VRAM does Krea-2-Raw need?

Krea-2-Raw with 12.8B parameters needs approximately 7 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is Krea-2-Raw better than other krea models?

Krea-2-Raw has 12.8B parameters with 8,192 context - a strong choice for image-generation.

What license is Krea-2-Raw under?

Krea-2-Raw is released under the Other license, making it suitable for most commercial and personal projects.

What hardware runs Krea-2-Raw well?

With 12.8B parameters, Krea-2-Raw requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for Krea-2-Raw?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~9 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

What models compete with Krea-2-Raw?

Krea-2-Raw competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec