Hacker News Reader

If you don't have a house with space that you expect to stay in for awhile, laptop+cloud is too compelling to make anything else worth it.

If you start having physical space guarantees, then the calculus changes...

View on HN

Last time I did the math, by the time I spent 4090 money on compute, I could have been done with a PHD. Now, if all you need is a 3060? Yeah you could probably make that work, but you wouldn't be doing LLM inference even quantized

Either you only use the GPU sporadically or your math is very different from Tim Dettmers` [1]:

"The break-even point for a desktop vs a cloud instance at 15% utilization (you use the cloud instance 15% of time during the day), would be about 300 days ($2,311 vs $2,270):"

And that was written before the current GPU crunch and assumes availability in the cloud, which currently is not a given at all.

[1] https://timdettmers.com/2023/01/30/which-gpu-for-deep-learni...

Thanks for the source! Very helpful for future reference.

Reply on news.ycombinator.com