Comment by WarmWash
9 hours ago
>Let’s address the elephant in the room first: why bother with local AI at all when cloud frontier models are better and often faster?
Ehh, the actual elephant in the room is:
"why bother with local AI at all when you can lease a GPU for $5/hr?"
To which the answer is you shouldn't bother, unless you have a bunch of money to throw at hobby projects.
$5/hr = $3600/mo.
Unless you only need the AI available some of the time, $5/hr is pretty expensive. That's an RTX Pro twice a year.
If you're using it for discrete sessions of coding or something, that might make sense for you but if you're using it for an always-on assistant, that pricing kinda sucks.
I would imagine extremely few people are utilizing an H200 for every hour of a month. Especially for something like an assistant
5090's are like $0.20/hr
> unless you have a bunch of money to throw at hobby projects.
there are lots of people with very expensive hobbies, see sailboat racing for example.