Oriel — AI & technology worth noticing, every day.

LLM inference, visually explained: why a 13B model reads 26 GB per token

Web page · https://youtube.com/watch?v=R3meYJU7wEg

First seen by Oriel on .

No saved summary available.

Metric trends

Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained

Points

Score reported by the source.

  • Hacker News: 3, latest observation

Comments

Comment count reported by the source.

  • Hacker News: 0, latest observation

Aliases

SourceExternal IDURL
Hacker News50447378https://www.youtube.com/watch?v=R3meYJU7wEg Read discussion