Two RTX 3060s, One Local 27B Model, and a GPU Unlock Experiment

shane@greaves.casa (Shane Greaves) — Mon, 26 Oct 2026 15:43:59 -0500

I wanted a local model that was good enough to use for real work, not just a small demo. My current favorite is a 27B Qwen model, so instead of swapping it out for something smaller, I put two 12 GB RTX 3060s to work in the same inference box.

The machine is called Moqorro. It runs Debian 12 and serves the model through the CUDA build of llama.cpp. Marwyn, my Hermes agent, can select this local model for private tasks while keeping its usual cloud model as the default.

GPU Unlock on Guru Dude

Two RTX 3060s, One Local 27B Model, and a GPU Unlock Experiment