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 : 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 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 Diff…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy