News for hackers. Stuff that matters.

A comment on Running large language models like ChatGPT on a single GPU. Parent comment

Re:Running large language models like ChatGPT on a single GPU by pclmulqdq on Monday February 20, 2023 @01:27PM (#34871059)
Cloud accelerators carry a huge price premium because there aren't very many of them available and they aren't as fungible as CPUs. Comparing to a local GPU would likely be favorable for the local machine.
[ Parent | on HN ]

There are no comments on this comment yet.