Krea 2 on a single RTX 4090: quantizing a 12B image model with GGUF
中文摘要
Krea 2 Turbo，12B云端图像模型，经GGUF量化，可在RTX 4090上本地运行。
English Summary
Krea 2 Turbo, a 12B cloud image model, now runs locally on an RTX 4090 via GGUF quantization.
原文节选
Krea 2 Turbo is a 12-billion-parameter diffusion transformer that normally lives in the cloud. Continue reading on Medium »