jack

jack

my quick posts!

time to listen to #kattdo in full (over next few days)

aperture was pretty good, excited to hear the rest!

@BennettBuhner Rlly??? Gonna have to keep looking around, currently just using ollama and whilst it’s somewhat decent speeds, it’s taking ages on reasoning

*note I’m running it on my Mac mini over SSH. I think my Mac desktop would be struggling rn and feel super buggy if I were to use it lol

not sure how well the benchmarks reflect everyday use, but the fact that a model as small as a 4b one can get higher than GPT-4o (ChatGPT’s “main” model for a while in a way) is CRAZY!

gonna try squeeze this onto my Mac mini (M2, 8/256 😅)