Should Run Your Own DNS with AdGuard Home Welcome back to Self-Hosted Tech! If you’ve been hanging around the homelab community for any amount of time, you’ve probably heard the term “DNS” thrown around constantly. Usually, it’s right next to words like “Pi-hole” or “AdGuard.” But if you’re new to the scene, you might be wondering: why does everyone care so much about DNS, and why should I run my own? ...

Self-Hosting Your First App with Docker: A Beginner’s Walkthrough Welcome back to Self-Hosted Tech! If you’ve been hanging around the homelab community, reading our blog, or watching our videos, you’ve probably heard the word “Docker” thrown around more times than you can count. You might be wondering what all the hype is about and, more importantly, how you can actually use it to run your own software. ...

Choosing Your First Local LLM Model: A Beginner’s Guide Welcome back to Self-Hosted Tech! If you’ve been following the explosion of AI over the last couple of years, you might be feeling a mix of awe and mild annoyance. On one hand, tools like ChatGPT and Claude are incredible. On the other hand, relying on the cloud means you are at the mercy of subscription fees, internet outages, and corporate privacy policies. ...

Stop paying for five AI subscriptions. Every major cloud AI tool has a self-hosted replacement that runs on your own hardware — free, private, and uncensored.

Q4 vs Q8 vs F16 — what do these numbers mean, and why does your model size change so drastically? A beginner-friendly guide to quantization and GGUF format for local LLMs.

Llama, GLM, Qwen, Mistral — what’s the difference, what fits your GPU, and which one should you run first? A practical beginner’s guide to choosing a local LLM.

Wire n8n to Ollama and build automated AI workflows — content generation, summarization, email processing, and more. All local, all free.

GPU buying guide for local AI — VRAM tiers, benchmarks, and which models run on each card.

Build a $351 mini PC that runs local AI, replaces ChatGPT, and pays for itself in 4 months.

Real production AI infrastructure: 7 VMs, multiple GPUs, local LLMs, TTS, image gen, agents, and automation — all self-hosted, zero cloud.