This repository has been migrated to https://huggingface.co/nunchaku-tech/nunchaku-shuttle-jaguar and will be hidden in December 2025.

Model Card for nunchaku-shuttle-jaguar

This repository contains Nunchaku-quantized versions of Shuttle Jaguar, designed to generate high-quality images from text prompts. It is optimized for efficient inference while maintaining minimal loss in performance.

Model Details

Model Description

• Developed by: Nunchaku Team
• Model type: text-to-image
• License: apache-2.0
• Quantized from model: Shuttle Jaguar

Model Files

• svdq-int4_r32-shuttle-jaguar.safetensors: SVDQuant quantized INT4 Shuttle Jaguar model. For users with non-Blackwell GPUs (pre-50-series).
• svdq-fp4_r32-shuttle-jaguar.safetensors: SVDQuant quantized NVFP4 Shuttle Jaguar model. For users with Blackwell GPUs (50-series).

Model Sources

• Inference Engine: nunchaku
• Quantization Library: deepcompressor
• Paper: SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
• Demo: svdquant.mit.edu

Usage

• Diffusers Usage: See flux.1-schnell.py. Just replace the safetensors with the ones from this repository. Check our tutorial for more advanced usage.
• ComfyUI Usage: See nunchaku-flux.1-schnell.json. Just replace the safetensors with the ones from this repository.

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}
}