alt Hacker NewsIf you can’t do it cheaper on your own hardware it does make you wonder how much of the cost of inference those large LLM providers are eating? Datacenter hardware isn’t magic.
Replies
petu • today at 12:44 PM
Datacenter hardware can batch at large scale, probably over 90% more energy efficient per token than a MacBook.
Der_Einzige • today at 1:53 PM
Datacenter hardware might as well be magic compared to consumer. "Oh the F35 isn't magic compared to my M16 bro!"
Your personal hardware probably isn't running useful tasks 24/7. If you spend 60% of your 8h work day on full on agentic work, then your hardware is paying off for itself only 20% of available time.