Check my GPU

Image models ·

Z-Image

Backbone
6.2B
Native output
1024×1024
Default steps
50
License
apache-2.0
Released
2026-01

How to run it

Quantized files · GGUF for ComfyUI

Smaller GGUF versions for ComfyUI (with the ComfyUI-GGUF node). No sign-in needed; the model’s license still applies.

huggingface.co/unsloth/Z-Image-GGUF (opens in a new tab)

Original weights · Hugging Face

Full-precision files from Alibaba (Tongyi), for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/Tongyi-MAI/Z-Image (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Alibaba (Tongyi). The weights themselves download from Hugging Face.

github.com/Tongyi-MAI/Z-Image (opens in a new tab)

git clone https://github.com/Tongyi-MAI/Z-Image

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Peak GPU memory at the native output size. Offloading moves the text encoder, or the whole pipeline, to system RAM between steps.

Precision Everything on GPU Text encoder offloaded Sequential offload Download
FP16 22.7 GB 14.7 GB 6.5 GB Original weights (opens in a new tab)
FP8 12.6 GB 8.5 GB 4.4 GB Original weights (opens in a new tab)
Q8 GGUF 13.0 GB 9.0 GB 4.5 GB GGUF (opens in a new tab)
Q4 GGUF 10.1 GB 6.1 GB 3.5 GB GGUF (opens in a new tab)

Components

Best hardware for Z-Image

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at FP8.

Grade · points Hardware Precision Memory Time per output Fit
89 ptsExcellent (S) · 89 of 100 points: Model quality 36.9/45, Memory fit 25.0/25, Speed 12.6/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 FP16 22.7 GB / 32.0 GB 14 s Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 10.5/15, Memory use 15.0/15 AMD Radeon RX 9070 XT FP8 12.6 GB / 16.0 GB 20 s Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 10.5/15, Memory use 15.0/15 NVIDIA GeForce RTX 5080 FP8 12.6 GB / 16.0 GB 20 s Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 10.2/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER FP8 12.6 GB / 16.0 GB 22 s Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 9.6/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER FP8 12.6 GB / 16.0 GB 24 s Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 9.6/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti FP8 12.6 GB / 16.0 GB 25 s Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 12.1/15, Memory use 12.1/15 NVIDIA GeForce RTX 4090 FP8 12.6 GB / 24.0 GB 15 s Runs well
84 ptsGreat (A) · 84 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 11.5/15, Memory use 12.1/15 AMD Radeon RX 7900 XTX FP8 12.6 GB / 24.0 GB 17 s Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 7.6/15, Memory use 15.0/15 NVIDIA GeForce RTX 5060 Ti 16GB FP8 12.6 GB / 16.0 GB 39 s Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 7.4/15, Memory use 15.0/15 NVIDIA GeForce RTX 4060 Ti 16GB FP8 12.6 GB / 16.0 GB 41 s Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.