Model · Alibaba · Image-Gen
Z-Image-Turbo
A fast 6B open image model from Alibaba's Tongyi-MAI lab. A distilled version of Z-Image that makes a photoreal image in 8 steps and renders English and Chinese text accurately, on a 16 GB graphics card, under Apache 2.0.
- Modality
- Image-Gen
- License
- Apache 2.0 (Open)
- Parameter size
- 6B
- Released
- November 26, 2025
- Last verified
- October 28, 2026
- Runs locally
- Yes
What you need to run it
- Mac
- Yes. Any Apple Silicon Mac (M1 or newer) with at least 16 GB (32 GB recommended) of memory. Newer chips are faster, but memory is what decides whether it runs.
- Windows / Linux PC
- NVIDIA works best. A graphics card with at least 4 GB (16 GB recommended) of video memory.
- No graphics card
- Not practical. Too slow without a graphics card or Apple Silicon.
Fits a 16 GB graphics card, and runs on Macs through a community MLX build or stable-diffusion.cpp.
Numbers are for: 6B model; compressed builds fit 4 GB (stable-diffusion.cpp), the standard build fits 16 GB. Based on the maker’s own figures; where the maker gives only a graphics-card figure, the Mac memory is our estimate.
Strengths
- Apache 2.0 — no revenue cap or branding rules for commercial use
- Fits a 16 GB consumer graphics card
- Only 8 steps per image, so it is quick; sub-second on a data-centre H800
- Strong photorealism and accurate English and Chinese text in images
Weaknesses
- Turbo is distilled for speed: lower variety between images and not meant for fine-tuning — the lab points to the base Z-Image model for that
- Text-to-image only; editing needs the separate Z-Image-Edit model, which was still listed as not yet released
Try it
| Where | Type | Notes |
|---|---|---|
| Hugging Face | weights | Apache 2.0 |
| ModelScope | weights | Mirror of the weights |
| Hugging Face Spaces | hosted | Free demo |
Official sources
- Model card model
- GitHub github
- Technical report paper
- Project blog announcement
Change log
- — Added hardware requirements (Mac support, memory, NVIDIA). Source: the model card and README (16 GB graphics card; 4 GB with stable-diffusion.cpp); Mac memory is estimated.
- — Initial entry. Released 2025-11-26 per the GitHub README news, under Apache 2.0. Added 2026-10-28 from the popularity sweep: 12.1k GitHub stars, 730k Hugging Face downloads in the last month and 5.5k likes.
Esc