by nunchaku-ai
Open source · 10k downloads · 172 likes
Nunchaku Z Image Turbo is an AI model optimized for image-to-image generation, delivering high performance while minimizing resource requirements through advanced quantization techniques. It stands out for its ability to run efficiently on various types of GPUs, with versions tailored for Blackwell (50-series) cards and earlier models. The model offers multiple quality and speed settings, allowing users to balance inference speed with result accuracy. Ideal for applications requiring fast and lightweight image generation, it caters to both developers and content creators looking to integrate high-performance AI tools into their projects.
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!
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).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 |
@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}
}