←back to thread

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: 0s | source
Show context
UncleOxidant ◴[31 Mar 23 21:29 UTC] No.35393932[source]▶
What's the difference between llama.cpp and alpaca.cpp?
replies(1): >>35394076 #
1. cubefox ◴[31 Mar 23 21:44 UTC] No.35394076[source]▶
I assume the former is just the foundation model (which only predicts text) while the latter is instruction tuned.