A homelab census of 41 Docker and 9 LXC containers, and how one 6 GB GPU decides which AI agents run on local Ollama, OpenRouter or a subscription.
Homelab census: 41 containers, one 6 GB GPU, and where my AI agents run
Related
NZ Hansard Research with ztab + MCP — Lake Onslow
Query: How has the debate on lake onslow, and in general dry year battery storage, shifted over the...
Branch‑parallel draft distillation speeds text generation 3.6
SpecOPD stretches the viable draft window by over 40 %, as reported by the authors. The same...
Re-Encoding Before Upscaling Is Usually a Waste of a Generation (Measured)
Every upscaling tutorial says the same thing: "transcode to ProRes first, so the upscaler isn't...