It offloads to system memory, but since there are "only" 3 Billion active parameters, it works surprisingly well. I've been able to run models that are up to 29GB in size, albeit very, very slow on my system with 32GB RAM.
It offloads to system memory, but since there are "only" 3 Billion active parameters, it works surprisingly well. I've been able to run models that are up to 29GB in size, albeit very, very slow on my system with 32GB RAM.