---
title: nunchaku-z-image-turbo
canonical_url: "https://www.modelscope.cn/models/nunchaku-tech/nunchaku-z-image-turbo"
md_url: "https://www.modelscope.cn/models/nunchaku-tech/nunchaku-z-image-turbo.md"
repository: nunchaku-tech/nunchaku-z-image-turbo
last_updated: 2026-01-10
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Tongyi-MAI/Z-Image-Turbo
base_model_relation: quantized
parameters: 18.0B
tensor_type:
  - BF16
  - F8_E4M3
  - I8
library_name:
  - safetensors
  - pytorch
frameworks:
  - PyTorch
language:
  - en
downloads: 5361
stars: 27
tags:
  - image-editing
  - SVDQuant
  - Z-Image-Turbo
  - Diffusion
  - Quantization
  - ICLR2025
---

# nunchaku-z-image-turbo

> nunchaku-z-image-turbo - nunchaku-tech 在 ModelScope 开源的模型。Model Card for nunchaku-z-image-turbo

nunchaku-tech/nunchaku-z-image-turbo 是 ModelScope 魔搭社区上的 18.0B 参数text-to-image-synthesis模型，采用 Apache License 2.0 许可，基于 Tongyi-MAI/Z-Image-Turbo 构建。

- **Repository**: nunchaku-tech/nunchaku-z-image-turbo
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 18.0B
- **Base model**: Tongyi-MAI/Z-Image-Turbo
- **Tags**: image-editing, SVDQuant, Z-Image-Turbo, Diffusion, Quantization, ICLR2025
- **Downloads**: 5361
- **Stars**: 27
- **Last updated**: 2026-01-10

Source: https://www.modelscope.cn/models/nunchaku-tech/nunchaku-z-image-turbo

---

<p align="center" style="border-radius: 10px">
  <img src="https://huggingface.co/datasets/nunchaku-tech/cdn/resolve/main/nunchaku/assets/nunchaku_v2.png" width="30%" alt="Nunchaku Logo"/>
</p>

<div align="center">
  <a href=https://discord.gg/Wk6PnwX9Sm target="_blank"><img src=https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Finvites%2FWk6PnwX9Sm%3Fwith_counts%3Dtrue&query=%24.approximate_member_count&logo=discord&logoColor=white&label=Discord&color=green&suffix=%20total height=22px></a>
  <a href=https://huggingface.co/datasets/nunchaku-tech/cdn/resolve/main/nunchaku/assets/wechat.jpg target="_blank"><img src=https://img.shields.io/badge/WeChat-07C160?logo=wechat&logoColor=white height=22px></a>
</div>

# Model Card for nunchaku-z-image-turbo


This repository contains Nunchaku-quantized versions of [Z-Image-Turbo](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo), a high-performance image generation model. It is optimized for efficient inference while maintaining minimal loss in performance.



No recent news. Stay tuned for updates!

## Model Details

### Model Description

- **Developed by:** Nunchaku Team (thank [@devgdovg](https://github.com/devgdovg))
- **Model type:** image-to-image
- **License:** apache-2.0
- **Quantized from model:** [Z-Image-Turbo](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo)

### Model Files

**Data Type**: `INT4` for non-Blackwell GPUs (pre-50-series), `NVFP4` for Blackwell GPUs (50-series).
**Rank**:

- `r32` for faster inference,
- `r128` for better quality but slower inference,
- `r256` for highest quality (slowest inference).





### Base Models

Standard inference speed models for general use


| Data Type | Rank | Model Name | Comment |
|-----------|------|----------|---------|
| INT4 | r32 | [`svdq-int4_r32-z-image-turbo.safetensors`](./svdq-int4_r32-z-image-turbo.safetensors) |  |
|  | r128 | [`svdq-int4_r128-z-image-turbo.safetensors`](./svdq-int4_r128-z-image-turbo.safetensors) |  |
|  | r256 | [`svdq-int4_r256-z-image-turbo.safetensors`](./svdq-int4_r256-z-image-turbo.safetensors) |  |
| NVFP4 | r32 | [`svdq-fp4_r32-z-image-turbo.safetensors`](./svdq-fp4_r32-z-image-turbo.safetensors) |  |
|  | r128 | [`svdq-fp4_r128-z-image-turbo.safetensors`](./svdq-fp4_r128-z-image-turbo.safetensors) |  |





### Model Sources

- **Inference Engine:** [nunchaku](https://github.com/nunchaku-tech/nunchaku)
- **Quantization Library:** [deepcompressor](https://github.com/nunchaku-tech/deepcompressor)
- **Paper:** [SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models](http://arxiv.org/abs/2411.05007)
- **Demo:** [demo.nunchaku.tech](https://demo.nunchaku.tech)

## Usage

- Diffusers Usage: See [z-image-turbo.py](https://github.com/nunchaku-tech/nunchaku/blob/main/examples/v1/z-image-turbo.py). Check this [tutorial](https://nunchaku.tech/docs/nunchaku/usage/zimage.html) for more advanced usage.
- ComfyUI Usage: See [nunchaku-z-image-turbo.json](https://nunchaku.tech/docs/ComfyUI-nunchaku/workflows/zimage.html#nunchaku-z-image-turbo-json).

## Performance

![performance](https://huggingface.co/datasets/nunchaku-tech/cdn/resolve/main/nunchaku/assets/efficiency.jpg)

## Citation

```bibtex
@inproceedings{
  li2024svdquant,
  title={SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models},
  author={Li*, Muyang and Lin*, Yujun and Zhang*, Zhekai and Cai, Tianle and Li, Xiuyu and Guo, Junxian and Xie, Enze and Meng, Chenlin and Zhu, Jun-Yan and Han, Song},
  booktitle={The Thirteenth International Conference on Learning Representations},
  year={2025}
}
```