How do these compare to Apple's Foundation Models, btw? | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

rickdg 4 months ago | parent | context | favorite | on: Gemma 4 on iPhone

How do these compare to Apple's Foundation Models, btw?

simonw 4 months ago | [–]

So much better. Hard to quantify, but even the small Gemma 4 models have that feels-like-ChatGPT magic that Apple's models are lacking.

snarkyturtle 4 months ago | [–]

AFM had a 4096 token context window and this can be configured to have a 32k+ token context window, for one.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact