KREA 2 GGUFs needs about 8.6 GB of memory at Q4_K_M (a 7.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 5.5 GB (Q3_K_M) to 13.7 GB (Q8_0).
KREA 2 GGUFs – 12.9B parameter Diffusion Transformer for local multimodal workflows
KREA 2 GGUFs are 12.9B parameter Diffusion Transformer models quantized for low‑VRAM usage. They require a patched custom node for ComfyUI and specific support models for text encoding and VAE. The weights are available in multiple quantizations.
Good at
- Low‑VRAM inference
- Multimodal diffusion generation
- Custom node compatibility
Limits
- Requires patched custom node
- No vision support in base GGUF
- Large memory for higher quantizations
Best for
- Local diffusion art creation
- ComfyUI workflow integration
- Low‑resource inference
Who it’s for. Users who run diffusion models on consumer hardware and need a lightweight GGUF version of Krea‑2. Requires familiarity with ComfyUI and custom node setup.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 5.5 GB | 6.7 GB | Fits | Get file → | |
| Q3_K_S | 5.5 GB | 6.7 GB | Fits | Get file → | |
| Q3_K_M | 5.5 GB | 6.7 GB | Fits | Get file → | |
| Q3_K_S | 6.1 GB | 7.3 GB | Tight | Get file → | |
| Q4_K_M | 7.2 GB | 8.6 GB | Too big | Get file → | |
| Q4_K_M | 7.3 GB | 8.6 GB | Too big | Get file → | |
| Q4_K_S | 7.3 GB | 8.6 GB | Too big | Get file → | |
| Q5_K_S | 8.8 GB | 10.4 GB | Too big | Get file → | |
| Q5_K_M | 8.9 GB | 10.4 GB | Too big | Get file → | |
| Q5_K_S | 8.9 GB | 10.4 GB | Too big | Get file → | |
| Q6_K | 10.5 GB | 12.3 GB | Too big | Get file → | |
| Q6_K | 10.6 GB | 12.4 GB | Too big | Get file → | |
| Q8_0 | 13.6 GB | 15.8 GB | Too big | Get file → | |
| Q8_0 | 13.7 GB | 15.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M or Q4_K_S (est. 8.6 GB at 8k context). For 12 GB VRAM, Q5_K_S or Q5_K_M (est. 10.4 GB). For 16 GB VRAM, Q6_K (est. 12.3–12.4 GB). Higher quantizations need more memory.
What GPU do you need for KREA 2 GGUFs?
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 (6.1 GB file, about 7.3 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (8.9 GB file, about 10.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (13.7 GB file, about 15.9 GB in use).
Which KREA 2 GGUFs quant should you choose?
Q4_K_M is the usual starting point for KREA 2 GGUFs: it balances file size and quality well. Here it is a 7.2 GB file.
The Q8_0 file is 13.6 GB, about 1.9 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 Q3_K_M at 5.5 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 KREA 2 GGUFs
How much VRAM does KREA 2 GGUFs need?
About 8.6 GB at Q4_K_M with an 8K context window. That is the 7.2 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 2 GGUFs on an 8 GB GPU?
Yes, with Q3_K_S: 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 2 GGUFs GGUF?
It depends on the quant: Q3_K_M is 5.5 GB, Q3_K_S is 5.5 GB, Q3_K_M is 5.5 GB, Q3_K_S is 6.1 GB, Q4_K_M is 7.2 GB, Q4_K_M is 7.3 GB and 8 more.
Where can I download KREA 2 GGUFs GGUF?
The files are on Hugging Face in the realrebelai/KREA-2_GGUFs 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 2 GGUFs 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 2 GGUFs on 8 GB VRAM?
Yes, use Q4_K_M or Q4_K_S which estimate 8.6 GB memory at 8k context.
What custom node is required to load these weights?
Clone RealRebelAI/ComfyUI-GGUF_KREA-2 into ComfyUI/custom_nodes/ and use UnetLoaderGGUF.
Do I need additional models for inference?
Yes, place Qwen3-VL-4B-FP8-Scaled.safetensors as CLIP and qwen_image_vae.safetensors as VAE in the models folder.