z image turbo nsfw v2 needs about 8.6 GB of memory at Q8_0 (a 7.2 GB file) with an 8K context window, so it fits on a 12 GB GPU.
Z-Image Turbo NSFW v2 – 6.15B parameter image model in Q8_0
Z-Image Turbo NSFW v2 is a 6.15‑billion‑parameter image model based on the lumina2 architecture. It is a direct GGUF conversion of the bf16 finetune and is quantized to Q8_0 to reduce VRAM usage while maintaining quality. The model is licensed under Apache‑2.0 and is intended for adult audiences only.
Good at
- Fast inference with low step counts (~8 steps)
- Low VRAM usage due to Q8_0 quantization
- Compatible with ComfyUI GGUF custom node
Limits
- No vision support beyond image generation
- Requires adult content compliance
- Only Q8_0 quant available
- No text‑only usage
Best for
- Low‑step image generation
- Rapid prototyping of adult image content
- ComfyUI integration
Who it’s for. Developers and artists who need a fast, low‑memory image model for adult content creation. The model is suitable for local inference on GPUs with limited VRAM, provided the user complies with the Apache‑2.0 license and local regulations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 7.2 GB | 8.6 GB | Too big | Get file → |
The Q8_0 file is 7.22 GB and requires approximately 8.6 GB of VRAM at 8k context. For GPUs with 8 GB or more VRAM, this quant is suitable. No other quantizations are available for this model.
What GPU do you need for z image turbo nsfw v2?
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 Q8_0 (7.2 GB file, about 8.6 GB in use).
Which z image turbo nsfw v2 quant should you choose?
Q8_0 (7.2 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about z image turbo nsfw v2
How much VRAM does z image turbo nsfw v2 need?
About 8.6 GB at Q8_0 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 z image turbo nsfw v2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of z image turbo nsfw v2 GGUF?
It depends on the quant: Q8_0 is 7.2 GB.
Where can I download z image turbo nsfw v2 GGUF?
The files are on Hugging Face in the lesliemore/z-image-turbo-nsfw-v2-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 z image turbo nsfw v2 use?
Hugging Face lists the license as apache-2.0. 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 this model on 8 GB VRAM?
Yes, the Q8_0 quant requires about 8.6 GB of VRAM at 8k context, so an 8 GB GPU is borderline but may work with lower context or batching.
Is this model suitable for non‑adult content?
No, the base finetune is NSFW and intended for adult audiences only. Use it only if you comply with local laws and platform terms.
What software is needed to run this model?
Place the .gguf file in ComfyUI/models/unet/ or models/diffusion_models/ and load it with the Unet Loader (GGUF) node, using the same text encoder and VAE as the original Z‑Image Turbo.