KR

Krea R Turbo

KreaGGUF by realrebelaiUpdated 2026-07-17
Download on Hugging Face
Parameters12.8B
Context—
Layers—
Architecturekrea2
Smallest quant4.8 GB
Quick answer

Krea R Turbo needs about 9.1 GB of memory at Q4_K_M (a 7.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 6 quants, from 4.8 GB (Q2_K) to 13.9 GB (Q8_0).

Krea R Turbo – a photorealistic portrait‑focused diffusion model

Krea R Turbo is a GGUF quantized version of Krea‑2‑Turbo merged with two style LoRAs. It focuses on photorealistic portraits while keeping sharp detail. The model is used with Qwen3‑VL 4B text encoder and Qwen‑image VAE.

Good at

  • Photorealistic portrait generation
  • Sharp detail preservation
  • Low‑step diffusion

Limits

  • No vision support beyond VAE
  • Requires Qwen3‑VL 4B text encoder and Qwen‑image VAE
  • License is other – not open source

Best for

  • Portrait photo editing
  • Fine‑detail image generation
  • Low‑step diffusion workflows

Who it’s for. Developers and artists who need a lightweight, photorealistic diffusion model for portrait work. It is suitable for ComfyUI users with the required text encoder and VAE.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.8 GB 5.9 GB
Fits Get file →
Q3_K_M6.1 GB 7.3 GB
Tight Get file →
Q4_K_M7.7 GB 9.1 GB
Too big Get file →
Q5_K_M9.3 GB 10.9 GB
Too big Get file →
Q6_K10.9 GB 12.7 GB
Too big Get file →
Q8_013.9 GB 16.1 GB
Too big Get file →

For an 8 GB VRAM card, Q3_K_M or Q2_K fit comfortably with the VAE and text encoder. If more VRAM is available, Q4_K_M or Q5_K_M can be used for higher quality. Larger quants like Q6_K or Q8_0 require low‑VRAM mode and will be slower.

What GPU do you need for Krea R Turbo?

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: the best quant that fits is Q2_K (4.8 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_M (6.1 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (9.3 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (10.9 GB file, about 12.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.9 GB file, about 16.1 GB in use).

Which Krea R Turbo quant should you choose?

Q4_K_M is the usual starting point for Krea R Turbo: it balances file size and quality well. Here it is a 7.7 GB file.

The Q8_0 file is 13.9 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 4.8 GB, with the quality trade-offs that come with fewer bits. 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturekrea2
Parameters12.8B

Source

Quantized byrealrebelai
FamilyKrea
Licenseother
Downloads (HF)3,156
Last updated2026-07-17

Frequently asked questions about Krea R Turbo

How much VRAM does Krea R Turbo need?

About 9.1 GB at Q4_K_M with an 8K context window. That is the 7.7 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 R Turbo on an 8 GB GPU?

Yes, with Q3_K_M: the 6.1 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Krea R Turbo GGUF?

It depends on the quant: Q2_K is 4.8 GB, Q3_K_M is 6.1 GB, Q4_K_M is 7.7 GB, Q5_K_M is 9.3 GB, Q6_K is 10.9 GB, Q8_0 is 13.9 GB.

Where can I download Krea R Turbo GGUF?

The files are on Hugging Face in the realrebelai/Krea-R-Turbo 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 R Turbo 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.

What text encoder and VAE are required?

The model requires Qwen3‑VL 4B text encoder and Qwen‑image VAE from the Comfy-Org/Krea-2 repack.

Does the model support negative prompts?

No, the model is distilled without a negative prompt; set CFG to 1.0 or 0.

Other GGUFs of Krea-2-Turbo

Similar models

Browse all →

More from realrebelai

All by realrebelai →

More Krea models

All Krea →

Other medium models

All medium models →