🚀 Z-Image Quantizer & Uploader

Convert the Z-Image or Z-Image-Turbo models to lower precisions (FP8, FP16, BF16) and push them directly to your own Hugging Face account.

How it works: This tool sequentially downloads, quantizes the selected files, and uploads everything. It is designed to run safely on free Spaces (16GB RAM) by processing files one at a time.

Hugging Face Token (Write Access Required)

Your Hugging Face Username

Source Repository

Components to Quantize

Select which parts of the model to convert. Unselected parts will be copied as-is.

text_encoder transformer

Quantization Precision

Target Repository (Auto-generated)

Operation Logs