Tongyi-MAI (Alibaba) · Apache 2.0

Z-Image-Turbo

A 6B image model that makes a picture in 8 steps and fits a 16 GB card. Apache 2.0.

How much memory it needs

Memory to run each model, from its model card or the size of its files. Smaller versions trade some quality for less memory.

ModelVersionNeedsBusiness use
Z-Image-Turbo4-bit GGUF4.0 GBAllowed
BF1616.0 GB

Which computers run it

The best model in this group for each machine.

ComputerBest versionFit
Laptop or PC, no graphics card, 32 GBZ-Image-Turbo 4-bit GGUFNeeds a graphics card
RTX 4060 · 8 GBZ-Image-Turbo 4-bit GGUFRuns great
RTX 3060 · 12 GBZ-Image-Turbo 4-bit GGUFRuns great
RTX 5060 Ti · 16 GBZ-Image-Turbo 4-bit GGUFRuns great
RTX 4090 · 24 GBZ-Image-Turbo BF16Runs great
RTX 5090 · 32 GBZ-Image-Turbo BF16Runs great
Mac with M4 · 16 GBZ-Image-Turbo 4-bit GGUFRuns great
Mac with M4 Pro · 48 GBZ-Image-Turbo BF16Runs great
Mac with M5 Max · 128 GBZ-Image-Turbo BF16Runs great
Ryzen AI Max+ 395 · 128 GBZ-Image-Turbo BF16Runs great
DGX Spark · 128 GBZ-Image-Turbo BF16Runs great
RTX PRO 6000 · 96 GBZ-Image-Turbo BF16Runs great
Mac Studio with M5 Ultra · 256 GBZ-Image-Turbo BF16Runs great
Mac Studio with M3 Ultra · 512 GBZ-Image-Turbo BF16Runs great

What it is good and bad at

Good at

  • Fast: 8 steps per image
  • English and Chinese text in images
  • Free for business

Not good at

  • GPU only in practice

Start it

  • Z-Image-Turbo: runs in ComfyUI (also diffusers, stable-diffusion.cpp (GGUF)). Model card