Personal AI Lab
KOEN
All topics

Local AI

  1. Building apps with AI on an 8GB iMac. So I ordered a Mac Studio.

    Notes on building apps on an 8GB M1 iMac, an Ollama Qwen experiment, external SSD trade-offs, and my Mac Studio order.

    HardwarePersonal AI Lab on 8GB
  2. Why Are Local LLMs Slow? — Prefill and Decode

    Why can an LLM take ages to start, then stream quickly? Prefill, decode, TTFT, KV caches, and a benchmark plan for the Mac Studio I am waiting for.

    Local AIOptimizing Local LLMs on Apple Silicon