Wild Krea 2 turbo NSFW needs about 9.5 GB of memory at Q4_1 (a 8.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 8.0 GB (Q4_1) to 13.6 GB (Q8_0).
Wild Krea 2 turbo NSFW – high‑quality image generation for mature prompts
Wild Krea 2 turbo NSFW is a 12.8 billion‑parameter Krea‑2 Turbo model fine‑tuned for NSFW content. It is available in two GGUF quantizations, Q4_1 and Q8_0, and requires a VAE and text encoder for optimal results.
Good at
- High‑quality NSFW image generation
- Fine‑tuned for mature prompts
- Compatible with ComfyUI workflows
Limits
- No vision support
- Requires external VAE and text encoder
- License is other – check terms
Best for
- Generating adult‑oriented images
- Creating mature art styles
- Testing NSFW prompt compliance
Who it’s for. Developers and artists who need a specialized image generator for mature content. The model is suitable for local deployment via llama.cpp or ComfyUI with the provided GGUF files.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_1 | 8.0 GB | 9.5 GB | Too big | Get file → | |
| Q8_0 | 13.6 GB | 15.8 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_1 file (8.02 GB, ~9.5 GB memory at 8k context). For 16 GB VRAM, the Q8_0 file (13.63 GB, ~15.8 GB memory at 8k context) offers higher precision. Memory estimates are approximate.
What GPU do you need for Wild Krea 2 turbo NSFW?
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: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q4_1 (8.0 GB file, about 9.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (13.6 GB file, about 15.8 GB in use).
Which Wild Krea 2 turbo NSFW quant should you choose?
Q4_1 (8.0 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Wild Krea 2 turbo NSFW
How much VRAM does Wild Krea 2 turbo NSFW need?
About 9.5 GB at Q4_1 with an 8K context window. That is the 8.0 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 Wild Krea 2 turbo NSFW on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Wild Krea 2 turbo NSFW GGUF?
It depends on the quant: Q4_1 is 8.0 GB, Q8_0 is 13.6 GB.
Where can I download Wild Krea 2 turbo NSFW GGUF?
The files are on Hugging Face in the ModdiAdam/Wild_Krea-2-turbo_NSFW repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Wild Krea 2 turbo NSFW 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 Wild Krea 2 turbo NSFW on 8 GB VRAM?
Yes, the Q4_1 quantized model is 8.02 GB and requires about 9.5 GB VRAM at 8k context, which fits on 8 GB VRAM with some overhead.
Do I need a VAE to use this model?
Yes, for optimal NSFW results use the qwen_image_vae.safetensors VAE and the qwen3vl_4b_fp8_scaled.safetensors text encoder.
Is this model suitable for non‑adult content?
The model is fine‑tuned for mature prompts and is intended for adult‑oriented content; it is not recommended for general use.