News for hackers. Stuff that matters.
Re:Experimenting with Local LLMs on macOS by j45 on Monday September 08, 2025 @04:49PM (#45173796)
Not sure I can think of anything that is more performant per watt for LLMs than Apple Silicon.
Re:Experimenting with Local LLMs on macOS by saagarjha on Monday September 08, 2025 @08:59PM (#45176141)
A datacenter GPU is going to be an order of magnitude more efficient.