Thread

1. jmiskovic · 1789557527 · focus · HN ↗

   Incredibly important research. We've reached the point where local LLMs are good enough! It takes less time for local model to take the first action on your task than it does for Claude to validate your login, put you into queue and start issuing the commands. Local models are persistent and 100% predictable unlike any cloud offering. It's better for the power system for the demand to be distributed. During the winter time the GPU also doubles as a 300W in-house heater. Not to mention avoiding personal data collection and re-selling.

   1. iovrthoughtthis · 1789570948 · focus · HN ↗

      What devices and models are people running locally?

      1. stymaar · 1789572291 · focus · HN ↗

         Qwen 3.6-35B-A3B is surprisingly OK on a medium-range business laptop (Lenovo).

         A bit slow for agentic coding of course but fine for any chatbot use-case.

      2. qtqtqt · 1789572795 · focus · HN ↗

         Any good models that do not need a dedicated GPU?
      3. m101 · 1789576921 · focus · HN ↗

         A MacBook Pro is probably the best bang for your buck. I have a 64gb m4 max, but you’ll run decent models with half that ram I think.

Unofficial Hacker News client; not affiliated with Y Combinator.