Blog is brand new - published write-ups are readable, and draft titles show what is currently being worked on.

Published

1 live

A NUT Server in an LXC, and a Grafana Dashboard to Watch It

Running Network UPS Tools inside a Proxmox container, passing the USB cable through, and turning battery runtime into a graph I actually look at.

Drafting

3 queued

Opus 5 Made vLLM as Easy as Ollama

vLLM is faster than Ollama and vastly harder to configure. Pair-debugging the memory math with a good model collapsed a weekend of flag-guessing into an evening.

How Good Is 8GB Nowadays?

What actually fits on a low-end GPU in 2026, why context length eats your VRAM faster than weights do, and the jobs an 8GB card is genuinely the right tool for.

Clustering Proxmox and Actually Turning On HA

Three nodes, a quorum device, ZFS replication instead of Ceph, and the fencing behavior nobody warns you about until your lights flicker.