Most useful quantized models of DEV(for less steps compared to the FULL version). Q2 for less than 8GB, Q4 for 12GB, etc
Quantized by https://huggingface.co/calcuis
more info and GGUF workflow, instructions at the FULL version:
https://civarchive.com/models/1477592/hidream-full-gguffp8workflow-q4-for-12gb-q2-for-8gb
