FL

krea

FluxGGUF by calcuisUpdated 2025-08-22
Download on Hugging Face
Parameters11.9B
Context—
Layers—
Architecturepig
Smallest quant3.9 GB
Quick answer

krea needs about 8.4 GB of memory at Q4_K_M (a 7.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 38 quants, from 3.9 GB (IQ1_S) to 47.6 GB (F32).

krea – a 11.9B Flux model quantized for GGUF inference

krea is a 11.9‑billion‑parameter Flux model, quantized by calcuis. It is available in multiple GGUF quantizations ranging from IQ1_S to Q8_0. The model is designed for text‑to‑image generation with a 8k token context.

Good at

  • Text‑to‑image generation
  • Efficient inference with low‑bit quantizations
  • Supports 8k context length

Limits

  • No vision support beyond image generation
  • Requires 8k context for full capability
  • License is other, not open source

Best for

  • Developers building lightweight image generation pipelines
  • Users with limited GPU memory
  • Experimenting with different quantization trade‑offs

Who it’s for. krea is suitable for developers and researchers who need a Flux‑based image generation model that can run on consumer GPUs. It is ideal for those who prefer GGUF quantizations for faster loading and lower memory usage.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.9 GB 4.9 GB
Fits Get file →
IQ1_M4.0 GB 4.9 GB
Fits Get file →
IQ2_XXS4.0 GB 5.0 GB
Fits Get file →
IQ2_XS4.0 GB 5.0 GB
Fits Get file →
Q2_K4.1 GB 5.1 GB
Fits Get file →
Q2_K4.1 GB 5.1 GB
Fits Get file →
Q2_K4.1 GB 5.1 GB
Fits Get file →
IQ2_S4.1 GB 5.1 GB
Fits Get file →
Q2_K_S4.1 GB 5.1 GB
Fits Get file →
Q2_K4.2 GB 5.2 GB
Fits Get file →
IQ3_XXS5.2 GB 6.3 GB
Fits Get file →
IQ3_S5.3 GB 6.4 GB
Fits Get file →
Q3_K_S5.4 GB 6.5 GB
Fits Get file →
Q3_K_M5.4 GB 6.5 GB
Fits Get file →
Q3_K_L5.5 GB 6.7 GB
Fits Get file →
IQ4_XS6.4 GB 7.7 GB
Tight Get file →
IQ4_XS6.6 GB 7.8 GB
Tight Get file →
IQ4_NL6.8 GB 8.1 GB
Too big Get file →
Q4_06.8 GB 8.2 GB
Too big Get file →
Q4_06.8 GB 8.2 GB
Too big Get file →
Q4_06.8 GB 8.2 GB
Too big Get file →
IQ4_NL6.9 GB 8.3 GB
Too big Get file →
Q4_06.9 GB 8.3 GB
Too big Get file →
Q4_K_S6.9 GB 8.3 GB
Too big Get file →
Q4_K_M7.1 GB 8.4 GB
Too big Get file →
Q4_17.7 GB 9.1 GB
Too big Get file →
Q5_08.4 GB 9.9 GB
Too big Get file →
Q5_K_S8.4 GB 9.9 GB
Too big Get file →
Q5_K_M8.5 GB 10.1 GB
Too big Get file →
Q5_19.1 GB 10.7 GB
Too big Get file →
Q6_K10.0 GB 11.7 GB
Too big Get file →
Q8_012.7 GB 14.7 GB
Too big Get file →
Q8_012.7 GB 14.7 GB
Too big Get file →
Q8_012.7 GB 14.7 GB
Too big Get file →
Q8_012.8 GB 14.9 GB
Too big Get file →
F1623.8 GB 27.2 GB
Too big Get file →
BF1623.8 GB 27.2 GB
Too big Get file →
F3247.6 GB 53.8 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S or IQ1_M (file size 3.93–3.95 GB, estimated 4.9 GB memory). For 12‑GB VRAM, IQ2_XXS or IQ2_XS (4 GB, 5 GB memory). For 16‑GB VRAM, Q4_0 (6.84 GB, 8.2 GB memory). Higher quantizations such as Q8_0 require 12.71 GB file size and 14.7 GB memory.

What GPU do you need for krea?

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 (4.2 GB file, about 5.2 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ4_XS (6.6 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (10.0 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (12.8 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (12.8 GB file, about 14.9 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (23.8 GB file, about 27.2 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (23.8 GB file, about 27.2 GB in use).

Which krea quant should you choose?

Q4_K_M is the usual starting point for krea: it balances file size and quality well. Here it is a 7.1 GB file.

The Q8_0 file is 12.7 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 IQ1_S at 3.9 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

Architecturepig
Parameters11.9B

Source

Quantized bycalcuis
FamilyFlux
Licenseother
Downloads (HF)6,696
Last updated2025-08-22

Frequently asked questions about krea

How much VRAM does krea need?

About 8.4 GB at Q4_K_M with an 8K context window. That is the 7.1 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 on an 8 GB GPU?

Yes, with IQ4_XS: the 6.6 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of krea GGUF?

It depends on the quant: IQ1_S is 3.9 GB, IQ1_M is 4.0 GB, IQ2_XXS is 4.0 GB, IQ2_XS is 4.0 GB, Q2_K is 4.1 GB, Q2_K is 4.1 GB and 32 more.

Where can I download krea GGUF?

The files are on Hugging Face in the calcuis/krea-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 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 on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations; they require about 4.9 GB memory at 8k context.

Does krea support vision tasks beyond image generation?

No, krea is focused on text‑to‑image generation and does not provide additional vision capabilities.

What is the context length supported by krea?

krea supports up to 8k tokens for full functionality.

Other GGUFs of FLUX.1-Krea-dev

Similar models

Browse all →

More from calcuis

All by calcuis →

More Flux models

All Flux →

Other medium models

All medium models →