News for hackers. Stuff that matters.

A comment on Llama.cpp guide – Running LLMs locally on any hardware, from scratch. Parent comment

Re:Llama.cpp guide – Running LLMs locally on any hardware, f... by LoganDark on Monday December 02, 2024 @03:35PM (#42300116)
That said though, there's currently no practical way to reach ChatGPT's performance locally, but I have hope that will change eventually. Of course, even today you can reach quite good performance locally, and for a lot of people it's more than good enough for their needs.
[ Parent | on HN ]

There are no comments on this comment yet.