https://www.linuxcolorado.com/tags/ollama/Recent content in Ollama on Linux ColoradoHugoen-USWed, 05 Aug 2026 00:00:00 +0000https://www.linuxcolorado.com/post/2026-08-05-ai-workstation-rtx3060-ollama/Wed, 05 Aug 2026 00:00:00 +0000https://www.linuxcolorado.com/post/2026-08-05-ai-workstation-rtx3060-ollama/<p>Several of my homelab projects want a local GPU for inference — running a vision LLM for OCR, offloading work that would otherwise hit a cloud API, keeping a small model resident and fast. So I built a dedicated box for it: a <strong>Dell Precision 3640</strong> (i3-10105F, 16 GB) with a <strong>Gigabyte RTX 3060 12 GB</strong>, running <strong>Ubuntu Server</strong> and serving a vision model through <strong>Ollama</strong>.</p> <p>Two things made this worth writing up. First, the actual GPU-serving setup has a few non-obvious choices (which driver, no CUDA Toolkit, exposing the port safely). Second — the fun part — I made the whole install <strong>zero-touch</strong>: plug in a USB stick, walk away, and the box comes up on a <strong>static IP with SSH pubkey auth ready</strong>, no monitor or keyboard ever attached. This post covers both, and both live as reusable docs/scripts in my <a href="https://github.com/vlouvet/infra-config"><code>infra-config</code></a> repo.</p>