Llama.cpp 30B runs with only 6GB of RAM now

(github.com)

1311 points msoad | 1 comments | 31 Mar 23 20:37 UTC | HN request time: 0.204s | source

1. nothrowaways ◴[01 Apr 23 07:25 UTC] No.35398033[source]▶

Somebody please teach ggreganov python. I am sure he will create same magic with python.