Z-Image Turbo
Frontierby Alibaba Tongyi-MAI
Ultra-fast image generation model from Alibaba Tongyi-MAI using S3-DiT architecture. 6B parameters, only 8 inference steps. Fits in 16GB VRAM.
VRAM requirements, GPU fit, and setup notes for Z-Image Turbo, including 8GB/12GB fit guidance where relevant. Recommended runtimes: ComfyUI and Diffusers support. Best download size: ~30.5 GB at BF16.
- Turbo distillation — only 8 steps for high quality
- 12.3B DiT with Qwen3 text encoder
- Competitive with FLUX.1 at fraction of the steps
- Apache 2.0 — fully open for commercial use
Your hardware
Detecting...
Image Quality Benchmarks
Measured quality metrics for Z-Image Turbo outputs.
How often humans prefer this model's output (0-100%)
Visual quality and composition rating (5-9 scale)
VRAM Requirements by Resolution and Precision
Compare which GPUs can run Z-Image Turbo at different precisions. FP8 uses less memory than FP16 when available, and the grade shows how comfortably each GPU handles the workload.
FP16 (full precision)
| Resolution | VRAM Required | RTX 4090 24GB | RTX 3060 12GB | RTX 4060 8GB | MacBook Pro M4 Pro 24GB |
|---|---|---|---|---|---|
| 512×512 | 21.9 GB | A | F | F | D |
| 768×768 | 22.0 GB | A | F | F | D |
| 1024×1024 | 22.3 GB | B | F | F | D |
Run with Python
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained(
"Tongyi-MAI/Z-Image-Turbo",
torch_dtype=torch.float16
)
pipe.to("cuda")
image = pipe(
prompt="your prompt here",
num_inference_steps=8,
guidance_scale=7.5,
height=1536,
width=1536,
).images[0]
image.save("output.png")Get started
Setup instructions for running Z-Image Turbo locally
1. Download the model
Get the checkpoint from HuggingFace
2. Place in:
ComfyUI/models/checkpoints/3. Launch ComfyUI
python main.pyMemory Breakdown
VRAM allocation at 1024×1024 on RTX 4090 24GB (24 GB)
Estimated Generation Time
Time per image at 1024×1024, 28 steps, FP16.
Sample Outputs
Available Formats, Downloads & Setup
Download Z-Image Turbo in the precision that matches your GPU. Lower precision usually means less VRAM pressure, while higher precision keeps more quality.
| Formato | Precisión | Tamaño | Proveedor | |
|---|---|---|---|---|
| safetensors | BF16 | 30.5 GB | official | Descargar |
LoRA Ecosystem
LimitedVery new model with limited LoRA support so far.
Related Workflows
You might also like
Frequently asked questions
FAQ — Z-Image Turbo VRAM, Runtimes & Fit
How much VRAM does Z-Image Turbo need?
Z-Image Turbo (6B parameters) requires approximately 22.3 GB of VRAM at FP16 precision for standard 1024×1024 image generation. If you want a lighter setup, lower precisions like FP8 can reduce memory use when available.
Can I run Z-Image Turbo on an 8GB GPU?
Z-Image Turbo usually needs more than 8GB for comfortable local use. Check the VRAM table above for the exact resolution and precision trade-off.
Does Z-Image Turbo work in ComfyUI and Diffusers?
Z-Image Turbo is marked for ComfyUI and Diffusers support in our catalog, so those are the runtimes we recommend first for local setup. If your workflow uses another front end, check the model's available formats and workflow notes above before downloading.
Can I run Z-Image Turbo on RTX 4090?
Z-Image Turbo can run on the RTX 4090 with sequential offloading enabled, though generation will be slower than native fit.
Does Z-Image Turbo support ControlNet?
There are currently no known ControlNet adapters for Z-Image Turbo. Check Hugging Face and Civitai for community-contributed adapters.
Does Z-Image Turbo have LoRA support?
Very new model with limited LoRA support so far. The LoRA ecosystem for Z-Image Turbo is rated as "minimal". Each LoRA adds roughly 0.3 GB of extra VRAM.
How fast is Z-Image Turbo?
On a reference GPU (RTX 4090 24GB), Z-Image Turbo generates a 1024×1024 image in approximately ~4.1s at FP16 with 28 inference steps. Faster GPUs with higher memory bandwidth will produce images more quickly.
About Z-Image Turbo
See also