Local Model Bench
  • Home
  • Cases
  • Methodology
  • About
Sign in Subscribe

privacy

A collection of 1 post
Flat editorial illustration: a vintage polygraph shows a perfectly flat line beside a silent mini computer; through the window a second chart runs wild
privacy

Is your local LLM actually local? We watched the wire

We packet-captured a Mac mini while Ollama, LM Studio and llama.cpp sat idle, loaded models and answered prompts. No packet we could attribute to a runtime carried anything out. What did cross the wire: update checks, a resolve call — and an OS that never stops talking.
03 Oct 2026 5 min read
Page 1 of 1
Local Model Bench © 2026
  • Sign up
Powered by Ghost