Local AI Server Build

In Progress

Why

I was tired of hitting API rate limits on Claude and OpenAI during development sprints. More importantly, I wanted to experiment with open-weight models (Llama 3, Mistral) without worrying about token costs or data privacy — everything stays on my network.

Architecture / Stack

Build Log

  1. Ordered parts from a mix of Newegg and used-marketplace deals (late January)
  2. Assembled barebones in February — first boot took three tries because I forgot to plug in the CPU cooler fan header, motherboard throttled immediately
  3. Installed Ubuntu Server 24.04 LTS headless with Docker + NVIDIA Container Toolkit
  4. Deployed Ollama as a systemd service behind a reverse proxy (Nginx on the host)
  5. Pulled Llama-3-8B-Instruct quantized to Q4_K_M — first inference was under 2 seconds for initial token

What Broke

The RTX 3090’s stock cooler is loud enough that my dog refused to enter the room during long training runs. Swapped to a water block mid-March, which meant disassembling everything and redoing cable management. Also learned that Docker volumes don’t survive an apt upgrade of nvidia-docker if you’re using bind mounts incorrectly — switched to named volumes across all containers.

What’s Next