logoalt Hacker News

dofm • today at 2:28 PM • 1 reply • view on HN

> At current prices ? those GPUs that are there now will be running there in 10 years still.

If they don't burn out after two or three. Annualized failure rates are about 9% according to Meta.

A quarter will have failed within three years. Less than half of the original hardware will be running after ten years. In both cases if you assume that rate does not increase over time. Do H100s come with replacement guarantees?


Replies

ericd • today at 2:49 PM

https://arxiv.org/pdf/2503.11901

This paper puts the failure rate of A100s closer to 0.3%/yr, H100s under 1%.

➕ show 1 reply