logoalt Hacker News

pants2yesterday at 5:41 PM3 repliesview on HN

Running them locally is cool and has privacy/autonomy benefits, but you can't really make a value case for it. Guaranteed if you run the math you will never run enough inference to pay off your hardware vs buying tokens. Last time I ran the math on my MBP I'd have to run inference 24 hours a day for 5+ years to pay off the cost of my MBP, not accounting for electricity costs.


Replies

iooiyesterday at 5:53 PM

Is this because of the tok/s? Since it's pretty easy to run up a $5k bill in API usage for Claude/ChatGPT in a month.

show 1 reply
slopinthebagyesterday at 7:55 PM

The value of not having a reliance on a third party company, and not needing an internet connection, and having total privacy: ∞

fragmedeyesterday at 8:29 PM

Just have to put some numbers on privacy and autonomy. What's the fine to my company if I get hacked and leak all my customer's PII? What's the cost in productivity lost if OpenAI/Anthropic/Google decides to suspend my account for an unknown reason?