News for hackers. Stuff that matters.

A comment on Ask HN: Recommendations for Local LLMs in 2024: Private and Offline?.

Re:Ask HN: Recommendations for Local LLMs in 2024: Private a... by nickdothutton on Saturday April 06, 2024 @01:32PM (#39953951)
My kingdom for a local LLM supporting my trusty Intel MacPro and AMD RX6900 XT!
[ Parent | on HN ]
Re:Ask HN: Recommendations for Local LLMs in 2024: Private a... by Havoc on Saturday April 06, 2024 @02:41PM (#39954447)
You should be able to run something via openCL and llama.cpp on it
[ Parent | on HN ]
Re:Ask HN: Recommendations for Local LLMs in 2024: Private a... by tharmas on Tuesday April 09, 2024 @01:59PM (#39982194)
This video demonstrates using LM Studio to run an LLM on an RX 7600XT 16gb so you should be able to run it on an RX 6900XT: https://www.youtube.com/watch?v=VXHryjPu52k
[ Parent | on HN ]