A personal system powering media, knowledge, and AI for my family — explained simply.
Long before Netflix existed, I had a simple dream: every movie, song, audiobook, and book I loved, available instantly at home — on my terms, with no subscription and no one else deciding what I could watch.
It started with VHS tapes that took over floors and walls. Then came DVDs, which eventually demanded entire walls of shelving. When the DVD burning era arrived, I saw the future and made the jump to digital files stored on ZIP disks and hard drives. That decision, more than twenty years ago, set me on the path of building something most people now pay monthly for.
Today, that vision lives on LeoneNAS 7 (our 73 TB media vault) coupled with LeoneMini-2 (our dedicated AV1 media engine) — a complete personal media empire for my family and close friends. Thousands of movies, TV shows, albums, audiobooks, comics, and books, perfectly organized and instantly streamable to any device, anywhere. No algorithms. No ads. No data harvested.
The same mindset that drove me from VHS to a self-hosted media library — own it, understand it, improve it — is exactly why I built LeoneNAS 9 for AI. These machines have become both a playground and a classroom, not just for me, but for my sons.
While most of the world rushed to use AI through cloud services, I chose to build it myself. Over the last year and a half, I’ve been building, breaking, and rebuilding AI servers because I wanted to understand these systems from the ground up — not just consume them.
Artificial intelligence is the most significant technological shift since the internet. Those who understand how it works at the infrastructure level will have a real advantage.
LeoneNAS 9 is my dedicated AI laboratory. By running powerful models locally instead of sending everything to corporate clouds, I maintain complete sovereignty over my data, my conversations, and my knowledge.
The deepest purpose is my sons. Both already show strong technical aptitude. I want them to grow up with an intimate, hands-on understanding of AI — how to run it, modify it, and trust it. This project gives them a living classroom in systems engineering, open-source architectures, and local AI orchestration.
It’s about building something that belongs to us — a foundation of knowledge and independence they can inherit and build upon for the rest of their lives.
LeoneNAS-7 & LeoneMini-2
The AI Brain
Purpose-built hardware nodes operating on Proxmox VE 9.2.5 and QTS 5.2.9
Click any topic to expand. Everything starts closed.
What is it? Large Language Models are AI systems trained on enormous amounts of text. “Inference” is the process of the model actually thinking and generating a response in real time.
Running inference locally on LeoneNAS 9 means all of this computation happens in my house. Nothing is sent to OpenAI, Google, or Anthropic. Your conversations stay completely private.
Llama is a family of powerful open-source AI models from Meta. Ollama makes it easy to download and run them locally with excellent reasoning and conversation quality.
A private, feature-rich chat interface that connects directly to Ollama. It supports voice, document processing, multi-user access, and RAG — making advanced local AI easy for the whole family to use.
Normal LLMs have no knowledge of your specific life or documents. RAG fixes this by searching your private files first, then feeding the most relevant pieces to the model before answering. The result is grounded, accurate, and personal.
My personal AI twin running on LeoneNAS 9. Powered by Ollama and OpenWebUI. It knows my projects, business docs, family stories, and homelab knowledge — and can answer questions about them accurately.
Beyond answering questions, generative AI can create images, artwork, event graphics, and more. On LeoneNAS 9 we run local models (Stable Diffusion, Flux, etc.) so everything stays private and under our control — no Midjourney accounts or data leaving the house.