Guides
Every practical guide on this site, grouped by topic. Pick the area you are working in.
All guides
-
Can a Mini PC Run a Local AI Model?
Can a cheap mini PC run a local LLM? Yes. We ran an 8B model on CPU-only hardware and measured it. Here is what it…
· -
Immich vs Google Photos: Can You Actually Replace It?
Immich is the credible answer to ‘I want to stop using Google Photos.’ Here is where it matches, where it still falls short, and the…
-
Tailscale vs Cloudflare Tunnel for Your Home Server
Tailscale and Cloudflare Tunnel both keep your inbound ports closed, but they work in opposite directions. Here is what connects to what in each, the…
-
Jellyfin vs Plex: Which One Fits Your Home Server?
Jellyfin and Plex do the same job but make different bets on price, transcoding, and who controls your data. A no-crown comparison to help you…
-
Access Jellyfin from Outside Your Home Network
Getting Jellyfin to work off your home network comes down to one question: who connects to whom. Here are the three real options, their trade-offs,…
-
How Much RAM Does a Local LLM Need?
Sizing a local LLM to your machine is arithmetic, not guesswork. Here is the formula, three models measured on one box, and the honest trade-off…
· -
How Many 4K Streams Can Your Home Server Transcode?
How many simultaneous 4K streams can your home server actually transcode before the picture buffers? We measured it on real hardware, with the numbers that…
-
Open WebUI in Docker: A Chat UI for Local LLMs
One Docker container turns a local model into a chat app the whole house can use. The tested two-container Ollama stack, first login, connecting the…
· -
llama.cpp vs Ollama vs LM Studio: Which to Use
Three front ends for the same GGUF models, compared with real lab numbers: control versus convenience versus a desktop app — and a clear recommendation…
·