Welcome to the CyberTron Project
Building CyberTron - The $150 AI Server

CyberTron didn't start as a carefully engineered AI server. It started with an old Craigslist computer, some spare eBay hardware, and one question:

How far can I push this thing?

The goal is to build a genuinely useful private AI system without spending thousands of dollars on enterprise hardware or sending everything into somebody else's cloud.

Along the way, we're upgrading the machine, experimenting with local language models, building AI assistants, breaking things, fixing things, and finding out where inexpensive hardware succeeds — and where it falls flat.

This page follows the entire project from the original $150 machine forward.

Latest Project Updates

Building CyberTron — Running LLMs Locally

Testing Qwen models, GPU inference, and the software stack that finally gave CyberTron a brain.

CyberTron finally moves beyond hardware upgrades and starts doing what it was built for: running local AI. In this chapter, I put Ollama, Open WebUI, and the RTX 3060 to work, test Qwen models up to 14B, and see how far a $150 AMD FX-era machine can really go as a private AI server.

 

Tuesday, August 25, 2026/Author: Roggie D/Number of views (35)/Comments (0)/ Article rating: No rating
RSS
Ubuntu Docker Ollama Open WebUI SearXNG Langfuse ComfyUI n8n

The key change is:

 

Follow Us on FacebookFollow Us on XFollow Us on InstagramSubscribe to our Youtube ChannelSubscribe to our Rumble Channel