Model Card for nunchaku-z-image-turbo
This repository contains Nunchaku-quantized versions of 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)
- Model type: image-to-image
- License: apache-2.0
- Quantized from model: Z-Image-Turbo
Model Files
Data Type: INT4 for non-Blackwell GPUs (pre-50-series), NVFP4 for Blackwell GPUs (50-series).
Rank:
r32for faster inference,r128for better quality but slower inference,r256for 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 | |
| r128 | svdq-int4_r128-z-image-turbo.safetensors | ||
| r256 | svdq-int4_r256-z-image-turbo.safetensors | ||
| NVFP4 | r32 | svdq-fp4_r32-z-image-turbo.safetensors | |
| r128 | svdq-fp4_r128-z-image-turbo.safetensors |
Model Sources
- Inference Engine: nunchaku
- Quantization Library: deepcompressor
- Paper: SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
- Demo: demo.nunchaku.tech
Usage
- Diffusers Usage: See z-image-turbo.py. Check this tutorial for more advanced usage.
- ComfyUI Usage: See nunchaku-z-image-turbo.json.
Performance
Citation
@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}
}