Microgpt in pure C hits 10M tps on Apple m5

(github.com)

33 points | by dhorthy a day ago ago

5 comments

  • ilaksh 22 minutes ago

    This is not an LLM obviously , it's just for generating random names. But interesting to think of the possibilities of truly tiny language models if there were connected together.

    • dcow 12 minutes ago

      Is token rate a function of parameter size?

  • throwa356262 an hour ago

    And the 5 years old AMD Ryzen 5 5600H is doing 7M?

    Am I reading this right? Then I need to try this on Strix Halo

  • fwip 28 minutes ago

    Model is 4K parameters - I don't know enough about that size of model to know if this impressive or not.

    • altcognito 9 minutes ago

      It's a trivial example. This won't be useful outside of a VERY specific domain without more parameters. Many people need to know about the bitter lesson.

      https://en.wikipedia.org/wiki/Bitter_lesson

      Over time, I'm sure we'll be able to filter information better and get parameter counts down, but I wouldn't count on that within the next 6 months.