Z Image Turbo – A native model with 4 megapixel output

Z Image Turbo Bringing back something that was missing with some of the newer models like the Flux 2 Dev, Van 2.2, Kevin Image… the ability to run it natively! Of course some of these other models are available in quantity versions but this has been eliminated so far that your results will not be as good as the original but it will satisfy your local running needs.

however, Z Image Turbo The model fits and runs very well on my RTX4080 with only 16GB of VRAM. It should also run on most consumer grade GPUs under 16GB. The model was posted online Hugging Face website.

The model has since been ported to Comfyui and files available online Direct download.

Model download and storage location

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 diffusion_models/
│   │   └── z_image_turbo_bf16.safetensors
│   ├── 📂 vae/
│   │   └── ae.safetensors
│   └── 📂 text_encoders/
│       ├── qwen_3_4b.safetensors

Once your models are arranged you can download the workflow I created using subgraphs which greatly simplifies the workflow. I cover how to create and use subgraphs in Comfyui in mine YouTube video.

The workflow will get you started using ZImage Turbo.

If you would like to support our site, please consider buying us Co-Fifor , for , for , . Grab a product or Subscribe. Need a faster GPU, get access to the fastest GPUs for less than $1 per hour runpod.io