Thread

1. eggbrain · 1790784864 · focus · HN ↗

   Performance optimizations don't just help the western labs, they also help with running more powerful/useful LLMs locally.

   If local LLMs get "good" enough, people will soon paying for subscriptions to ChatGPT and Claude, which hurts their revenue.

   1. kennywinker · 1790785414 · focus · HN ↗

      The only thing preventing this switch from starting in earnest is the data center buildout monopolizing all current and future GPUs

      1. lumost · 1790785584 · focus · HN ↗

         The margins on NVidia datacenter hardware are ... high. At least one order of magnitude larger than a consumer chip.

         Given the recent deepseekv4.1 advances - how good of a 3B model can we make to run on an iphone natively? is it good enough to match common muse/dot use cases for consumers? the phone is already always on.. no need for a cloud server.

         1. christkv · 1790787957 · focus · HN ↗

            any model you run on a phone is not going to do wonders for you battery life

Unofficial Hacker News client; not affiliated with Y Combinator.