You are assuming people need the models they use today. The reality is much much... | Hacker News

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

iwontberude 71 days ago | parent | context | favorite | on: Running Gemma 4 26B at 5 tokens/sec on a 13-year-o...

You are assuming people need the models they use today. The reality is much much smaller models will suffice (i.e. dont use god models for dog work)

kennywinker 71 days ago [–]

I’m not assuming that at all, I’m responding to someone suggesting we’ll be able to run 1T models on phones in 2-ish years.

I absolutely agree that models are going to advance on to “edge” hardware over the next few years by becoming small + specialized.

iwontberude 71 days ago | [–]

Sorry to put words in your mouth, totally agree

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