Welcome. Let's get AI running on your own hardware.

Your first model on the computer you already own.

• How to run AI locally: your first model in ten minutes
• Is running AI locally worth it? Local vs ChatGPT, honestly
• Ollama commands cheat sheet: every command you'll actually use
• Run an LLM on CPU only: local AI on a laptop without a GPU

Memory, quantization, and why one card is fast and another isn't.

• How much VRAM do you need to run an LLM locally?
• Quantization explained: Q4_K_M vs Q8 vs FP16
• Why memory bandwidth sets LLM speed (and how to estimate tokens per second)
• Mixture of experts explained: why a 30B model can run like a 3B

Which open model to run for what, at every memory size.

• The best local LLM for 8 GB of VRAM
• The best local LLM for 24 GB of VRAM (RTX 3090, 4090, 7900 XTX)
• The best local LLM for coding, by how much memory you have
• The best local LLM for 12 GB of VRAM (RTX 3060, 4070, B580)

Used GPUs, Macs, and builds, with what they really run.

• Buying a used RTX 3090 for AI: what to check and what to pay
• The Tesla P100 for local LLMs: 16 GB of HBM2 for under $100
• Running LLMs on a Mac: which M-series chip and how much memory
• The Tesla P40 for local LLMs: 24 GB cheap, but is it fast enough?

Ollama, llama.cpp, LM Studio, Open WebUI, and serving a team.

• Ollama vs llama.cpp vs LM Studio: which should you use?
• Set up Open WebUI: a private ChatGPT on your own computer
• llama.cpp server guide: run llama-server with the flags that matter
• LM Studio guide: download, run and serve local models

Chat with your documents, code with it, run agents, add voice.

• Chat with your documents locally, without uploading them anywhere
• A local coding assistant in VS Code: Continue, Cline and Ollama
• Local AI for Obsidian: chat with your notes privately
• Build a local voice assistant: Whisper, a local LLM and text-to-speech