Thread

1. drob518 · 1789655521 · focus · HN ↗

   One problem we’re going to have with AI hardware is coming up with a standard set of specifications that are comparable. I don’t really care about the CPU GHz and the memory bandwidth, at least not directly. What I really want to know is how many tokens per second this will deliver, but that also depends on the model. We need a standard metric for that. Perhaps we agree on a specific open weight model (e.g. GLM 5.3 Flash or Qwen vWhatever) and then measure TPS on the hardware of interest.

   1. swiftcoder · 1789655715 · focus · HN ↗

      > I don’t really care about the CPU GHz and the memory bandwidth ... What I really want to know is how many tokens per second this will deliver

      There is a fairly direct link between the two numbers. You can predict the latter from former reasonably well

Unofficial Hacker News client; not affiliated with Y Combinator.