Thread

1. reedf1 · 1790785294 · focus · HN ↗

   I've been running Qwen 3.8 27b (an opus 4.6 tier model), locally on a 5090 for just over two weeks @ 170 tokens/s. That's a frontier model from 9 months ago running on consumer hardware. Who knows where distillation and pruning gets us in another year.

   1. newyankee · 1790788738 · focus · HN ↗

      Do you think this trend can continue ? An Opus5.5 equivalent on a slightly bigger local hardware in under a year ?

      1. an0malous · 1790789188 · focus · HN ↗

         I’m not an AI researcher, but it seems like there’s a ton of waste having a universal model that knows everything when any individuals use case requires like generously 10% of what’s stored in the model. Does it even need to have memorized knowledge stored in the model or could it just look up info and docs like humans do? If all you need is the language and intelligence, I think Opus5.5 equivalent intelligence will run on an iPhone within 5 years.

Unofficial Hacker News client; not affiliated with Y Combinator.