Tongyi-MAI · 6B parameters · Apache 2.0
What GPU do you need to run Z-Image-Turbo?Memory and cards.
Z-Image-Turbo needs about 16 GB of GPU memory (VRAM) at its smallest (As released, the maker's figure), so a 16 GB card such as an RTX 4080 runs it. The cheapest card on our list that fits, an RTX 4060 Ti 16GB, costs about $0.14 an hour.
GPU memory
Z-Image-Turbo, by version.
Resolution, batch size, upscalers and extra LoRAs all add memory. How we work it out
| Version | Memory needed | Card size | Cards that fit | From |
|---|---|---|---|---|
| As released, the maker's figure | about 16 GB | 16–20 GB | RTX 4090, RTX 5090, RTX 3090, RTX 4080, RTX 3090 Ti, RTX 5080, RTX 5070 Ti, RTX 4070 Ti SUPER, RTX 5060 Ti 16GB, RTX 4060 Ti 16GB | $0.14/hr on an RTX 4060 Ti 16GB |
Fast: an image takes 8 steps instead of the usual 20 to 50. Good at photos and at writing text into pictures. Its maker says it fits comfortably on a 16 GB card. Apache 2.0, so commercial use is fine.
Run it
Start Z-Image-Turbo in minutes.
The rented machine downloads it straight from Hugging Face, not through your computer. On KernelMachine, Rent an Image maker with these files, below: they load into ComfyUI's model folders by themselves once it's ready. Already renting one? Pick it under Load from link on the rental's page, or run km load with each link. ComfyUI on a rented GPU
$ km load https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors
$ km load https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors
$ km load https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors
Files to load
Z-Image-Turbo in ComfyUI.
The files ComfyUI's own "Z-Image-Turbo: Text to Image" template uses, 20.7 GB in all. Each goes in its own folder, and Load from link puts it there. Then open that template from ComfyUI's template menu.
| File | Folder | Size |
|---|---|---|
| z_image_turbo_bf16.safetensors | models/diffusion_models | 12.3 GB |
| qwen_3_4b.safetensors | models/text_encoders | 8.0 GB |
| ae.safetensors | models/vae | 335 MB |
They start loading as soon as the rental is ready, straight from Hugging Face to the machine. Already renting an Image maker? Pick Z-Image-Turbo under Load from link on the rental's page. A card with 16 GB or more runs them.
Common questions
Questions, answered plainly.
How much VRAM does Z-Image-Turbo need?
As released, the maker's figure: about 16 GB.
Can an RTX 4090 run Z-Image-Turbo?
Yes. Z-Image-Turbo (As released, the maker's figure) needs about 16 GB, which fits in the RTX 4090's 24 GB.
Can I run Z-Image-Turbo on KernelMachine?
Yes. Rent an Image maker with these files, on this page, starts ComfyUI on the cheapest card with 16 GB or more, and the machine downloads each file from Hugging Face into ComfyUI's folders once it's ready. Already renting an Image maker? Pick Z-Image-Turbo under Load from link on the rental's page.
Other models
Compare with other image and video models.
Preparing an invite-only beta
Get an email when access opens.
No launch date is set. We'll email you once when KernelMachine opens. Nothing else.