Show HN: Selfhostllm.org – Plan GPU capacity for self-hosting LLMs

Posted by erans on Friday August 08, 2025 @01:49PM
from the show-hn dept.

A simple calculator that estimates how many concurrent requests your GPU can handle for a given LLM, with shareable results.

( 3 comments | 3 points | on HN )

Re:Show HN: Selfhostllm.org – Plan GPU capacity for self-hos... by erans on Friday August 08, 2025 @02:03PM (#44839827)

I also added a Mac version: https://selfhostllm.org/mac/ so you can know which models you can run on your Mac and get an estimated tokens/sec.

[ Parent | on HN ]

Re:Show HN: Selfhostllm.org – Plan GPU capacity for self-hos... by atmanactive on Friday August 08, 2025 @08:44PM (#44843123)

Very useful, thanks. I'm missing a reset button though.

[ Parent | on HN ]

Re:Show HN: Selfhostllm.org – Plan GPU capacity for self-hos... by harshnigam on Saturday August 09, 2025 @04:45PM (#44850032)

I see it doesn't take GPU performance into consideration when showing the estimates. H100 and A100 are performing the same. Am I doing it wrong?

[ Parent | on HN ]