Guides
Practical tutorials & how-tos
Step-by-step walkthroughs for running models locally and keeping your data yours.
Open Source AI Wins: Every Edition
Index of every Open Source AI Wins roundup, covering model releases, licence changes and open-source AI tooling milestones.
Open-Weight LLM Showdown: Every Edition
Index of every Open-Weight LLM Showdown edition, the recurring look at which open-weight models actually run on consumer hardware.
How to Choose a Local AI Model
Pick a local LLM that fits your hardware. Honest guidance on VRAM, quantization labels, model families, and the test that shows whether a model is useful.
⏱ 15-30 minutesHow to Run a Local LLM: A Beginner's Guide
Run an AI chat model on your own computer with Ollama or LM Studio, including honest hardware limits, setup steps, privacy checks, and troubleshooting.
⏱ 20-40 minutesHow to run an LLM locally on a Mac (2026)
Run a private, offline LLM on Apple Silicon in 2026 - Ollama and LM Studio, MLX vs GGUF, how much memory you need, and which models run well.
⏱ 10 min readHow to run an LLM locally on Windows (2026)
Run a private, offline LLM on Windows in 2026 - Ollama and LM Studio setup, native vs WSL2, the GPU and driver requirements, and which models fit your VRAM.
⏱ 9 min readHow to run an LLM locally on Linux (2026)
Run a private LLM on Linux in 2026 - the easy path with Ollama, the flexible path with llama.cpp, and the fast path with vLLM, plus GPU requirements.
⏱ 10 min readRun Your Own AI in 2026: The Complete Privacy-First Guide
Cloud AI trains on your prompts. Local AI does not. A step-by-step 2026 walkthrough of Ollama and LM Studio on Windows, Mac, and Linux.
⏱ 1-2 hoursAI Agent Containment: How to Sandbox Autonomous AI
When AI can hack systems autonomously, containment becomes critical. A practical guide to sandboxing AI agents, with configuration examples and security considerations.
⏱ 30-60 minutes