logoalt Hacker News

guerrillatoday at 12:03 AM3 repliesview on HN

> I’ll often kick off a process at the end of my day, or over lunch. I don’t need it to run immediately. I’d be fine if it just ran on their next otherwise-idle gpu at much lower cost that the standard offering.

If it's not time sensitive, why not just run it at on CPU/RAM rather than GPU.


Replies

weird-eye-issuetoday at 12:42 AM

Yeah just run a LLM with over 100 billion parameters on a CPU.

show 1 reply
grueztoday at 2:19 AM

Does that even work out to be cheaper, once you factor in how much extra power you'd need?

bethekidyouwanttoday at 12:12 AM

Run what exactly?

show 1 reply