FLUX.1 Krea dev needs about 8.3 GB of memory at Q4_K_M (a 6.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 5.2 GB (Q3_K_S) to 6.9 GB (Q4_K_M).
FLUX.1 Krea dev – 12 billion‑parameter image generation from text
FLUX.1 Krea dev is a 12 billion‑parameter rectified flow transformer that creates images from text descriptions. It offers high aesthetic quality and competitive prompt following. The model is open‑weight and can be used for personal, scientific, and commercial purposes.
Good at
- High‑quality aesthetic photography
- Efficient generation via guidance distillation
- Competitive prompt following
Limits
- Not intended for factual information
- May amplify societal biases
- Prompt following depends on style
Best for
- Creative image generation
- Aesthetic photography projects
- Artist workflow experimentation
Who it’s for. Developers and artists who need an open‑weight image generation model for creative projects. The model is suitable for research and commercial use under the provided license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 5.2 GB | 6.4 GB | Fits | Get file → | |
| Q4_K_S | 6.8 GB | 8.1 GB | Too big | Get file → | |
| Q4_K_M | 6.9 GB | 8.3 GB | Too big | Get file → |
For 8 GB VRAM use Q3_K_S (file size 5.23 GB, estimated 6.4 GB memory). For 10 GB VRAM use Q4_K_S (6.8 GB, 8.1 GB). For 12 GB VRAM use Q4_K_M (6.93 GB, 8.3 GB). Estimates are approximate.
What GPU do you need for FLUX.1 Krea dev?
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: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is Q3_K_S (5.2 GB file, about 6.4 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_M (6.9 GB file, about 8.3 GB in use).
Which FLUX.1 Krea dev quant should you choose?
Q4_K_M is the usual starting point for FLUX.1 Krea dev: it balances file size and quality well. Here it is a 6.9 GB file.
If memory is tight, the smallest file is Q3_K_S at 5.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about FLUX.1 Krea dev
How much VRAM does FLUX.1 Krea dev need?
About 8.3 GB at Q4_K_M with an 8K context window. That is the 6.9 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 FLUX.1 Krea dev on an 8 GB GPU?
Yes, with Q3_K_S: the 5.2 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FLUX.1 Krea dev GGUF?
It depends on the quant: Q3_K_S is 5.2 GB, Q4_K_S is 6.8 GB, Q4_K_M is 6.9 GB.
Where can I download FLUX.1 Krea dev GGUF?
The files are on Hugging Face in the InvokeAI/FLUX.1-Krea-dev-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 FLUX.1 Krea dev 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 FLUX.1 Krea dev on 8 GB VRAM?
Yes, using the Q3_K_S quantized file (5.23 GB) which requires about 6.4 GB of VRAM at 8k context.
Does this model provide factual answers?
No, it is not intended to provide factual information and may amplify biases.
Is the model suitable for commercial use?
Yes, outputs can be used for commercial purposes under the flux‑1‑dev‑non‑commercial‑license.