←back to thread

Show HN: I estimated the carbon impact of different LLMs

(modelpilot.co)
8 points aposded | 2 comments | 26 Aug 25 03:13 UTC | HN request time: 0.425s | source

(did my best with the data that is available online)
1. niek_pas ◴[26 Aug 25 10:24 UTC] No.45024607[source]▶
This is neat. It's a little hard to compare the best-performing models ("~ 0.00006232g" vs. "~0.00013746g" is not easy at a glance) --- perhaps better to use scientific notation, milligrams, or CO2e per 10M tokens?
replies(1): >>45025115 #
2. aposded ◴[26 Aug 25 11:34 UTC] No.45025115[source]▶
You're right! Fixed.