Live data from Hacker News

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

selfhostllm.org

Post reply on HN

Print view View original

1–4 of 4 posts

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

#1

Post by erans » Fri, Aug 08, 2025, 5:49 PM UTC

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

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

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

#2

Post by erans » Fri, Aug 08, 2025, 6:03 PM UTC

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.

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

#3

Post by atmanactive » Sat, Aug 09, 2025, 12:44 AM UTC

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

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

#4

Post by harshnigam » Sat, Aug 09, 2025, 8:45 PM UTC

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?

Post reply on HN