Thread

1. huseyinkeles · 1789704082 · focus · HN ↗

   Testing on a MBP m4 pro 24gb

   ~100t/s prefill, ~15t/s, dropping to ~10t/s later with 64k context.

   The issue is I have yet to find a useful agentic local llm that I can run on this machine.

   Just given a relatively simple task on a swift app, took 25 minutes, brainstorming like crazy but can not decide on what to do. Eventually I killed it. GPT 5.6 sol-medium took 3 minutes to complete the same task for reference.

   1. aetherspawn · 1789705238 · focus · HN ↗

      Gemma 30B with 256K context runs at 20 tok/sec on my M3 Max with 128GB RAM so I think there’s something wrong with your setup. This should run at ~30-40 toks. Maybe your inference engine is not optimised for Mac.

      1. piyh · 1789706433 · focus · HN ↗

         30B is useless on 24 gigs of ram as there's ~4 gigs of ram left for everything else even with unsloth quants

Unofficial Hacker News client; not affiliated with Y Combinator.