Z-Image Turbo
Alibaba · Tongyi-MAI/Z-Image-Turbo
Weights license: Apache 2.0 · code and components may use other terms
Quality
Quality · LMArena · text-to-image
LMArena 2026-10-07 · human-preference rating · higher is better · this model outlined
- Color = publisher
Source: LMArena 2026-10-07 · collected 2026-10-25 · dataset · CC BY 4.0 · models without a rating are not drawn (no rating ≠ 0)
1,083 ± 5 · LMArena · text-to-image · Confidence interval 1,078–1,089 · 24,808 votes
Artificial Analysis is excluded: its free tier is internal use only.
Reported by the publisher
Quality × memory
No comparable quality × memory pair
Image, video and audio models have no shared quality scale, and their memory comes from the publisher's documented minimum path, so quality is not charted against memory.
Consider Z-Image Turbo from Alibaba for the text-to-image task (6B parameters).
The catalog lists the publisher's documented memory path under Runs on and has not reviewed other configurations. Actual memory depends on precision, resolution, duration and offload; consult the official source.
Runs on
Enough memory 38
A publisher documents a path within this memory, on this platform (CUDA or Apple MPS). Conditional paths need offload or quantization.
Show all 38
One memory tier short 8
The same machines with the next memory size up would have enough.
Hardware profiles grouped by the publisher's documented minimum memory path and platform. Not a measured run.
Measured speed
No published measurement for this checkpoint
Generation time per image is shown only when a source publishes it with hardware, build and setup. It is never estimated.
How to run
Publisher-documented memory path: Official consumer-GPU fit. Actual memory depends on precision, resolution, duration and offload; consult the official source. Official hardware evidence
Documented ways to run it
Copied as printed in the linked source (read 2026-10-18); not run by this site.
pip install git+https://github.com/huggingface/diffusersimport torch
from diffusers import ZImagePipeline
# 1. Load the pipeline
# Use bfloat16 for optimal performance on supported GPUs
pipe = ZImagePipeline.from_pretrained(
"Tongyi-MAI/Z-Image-Turbo",
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=False,
)
pipe.to("cuda")
# [Optional] Attention Backend
# Diffusers uses SDPA by default. Switch to Flash Attention for better efficiency if supported:
# pipe.transformer.set_attention_backend("flash") # Enable Flash-Attention-2
# pipe.transformer.set_attention_backend("_flash_3") # Enable Flash-Attention-3
# [Optional] Model Compilation
# Compiling the DiT model accelerates inference, but the first run will take longer to compile.
# pipe.transformer.compile()
# [Optional] CPU Offloading
# Enable CPU offloading for memory-constrained devices.
# pipe.enable_model_cpu_offload()
prompt = "Young Chinese woman in red Hanfu, intricate embroidery. Impeccable makeup, red floral forehead pattern. Elaborate high bun, golden phoenix headdress, red flowers, beads. Holds round folding fan with lady, trees, bird. Neon lightning-bolt lamp (⚡️), bright yellow glow, above extended left palm. Soft-lit outdoor night background, silhouetted tiered pagoda (西安大雁塔), blurred colorful distant lights."
# 2. Generate Image
image = pipe(
prompt=prompt,
height=1024,
width=1024,
num_inference_steps=9, # This actually results in 8 DiT forwards
guidance_scale=0.0, # Guidance should be 0 for the Turbo models
generator=torch.Generator("cuda").manual_seed(42),
).images[0]
image.save("example.png")Evidence level: Publisher documentation linked; no execution reproduced by this site.
Before downloading
- Check the exact checkpoint and license linked here.
- Confirm a compatible runtime and precision or quantization for your platform.
- Allow for context, batch size and any extra media components beyond the weights.
Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / version
- Tongyi-MAI/Z-Image-Turbo
- Task and modality
- text-to-image · image
- Count and basis
- 6B · manufacturer model card
- Released
- Tongyi-MAI/Z-Image README (GitHub), News · read 2026-10-09source
- Published repository size
- 32.9 GBNot runtime memory or a minimum download.files
- Published components
- Technical details pending review
- Runtime and precision
- No local execution verified.
- Commercial use
- Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
License, parameter count and release date come from the publisher's sources listed on this page (a date no source states is left empty). The hardware requirement has not been reviewed, so memory is a labelled estimate. The repository size, when shown, is the full published download.
Sources
Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.
- Publisher checkpoint and model card
- Weight license and use terms
- Quality benchmark source · Artificial Analysis image · excluded (free tier is internal use only)
- Publisher hardware documentation
Catalog reviewed: 2026-09-22.




































