I read the CSV from the first overnight benchmark of eight small LLMs on a Pi 4B (2026-10-26). Generation ran at 2.4 to 5.1 tokens per second, the smallest model was fastest, and longer context slowed each model by a different amount.
The Pi overnight LLM experiment queued on 2026-10-14 produced its first results only on the night of Oct 26–27. A VS Code server process blocked it each night, and after a reboot the schedule itself was gone.
This blog runs on one Pi 4B: Hugo builds static HTML, Caddy serves it, and a Cloudflare Tunnel publishes it by opening the connection outward. Nothing connects in from outside.