Start here
New to local AI? This page takes you exactly where you need to go, in two steps. Pick your level, say what you want to do, and you get the right path of articles — no fluff, no commitment.
The basics, in six reads
Six articles that answer the fundamental questions — in reading order, no prerequisites.
What is local AI and why you need itThe model runs on your machine, not on a server: what changes, what you gain, and how to get started in five minutes.Running LLM Models Locally: From First Install to First Working ModelFrom zero to a first answering model: what you actually need, Ollama step by step, how to pick a model for your memory, expected speeds per hardware, and the typical problems fixed.Where local models learn: open weights explained without the fluffThe model doesn't hook into the internet for its abilities: it absorbed them once at pre-training and executes them on your hardware. Open weights isn't open data, and the models come from many labs, not one.Frontier vs local AI: the honest comparison nobody makesFrontier models are still more powerful on complex cases, but cost is the last thing that decides: the table, the break-even point and the honest answer to "front-load and then ride for free?".Privacy and GDPR: What Local AI ChangesExtra-EU transfers, sub-processors, Arts. 5, 25, 28, 32 and 44: what the GDPR really says about cloud vs local, and what is still owed even with in-house AI.Costs: local vs API, done with real numbersHow much does local really cost compared to a cloud API? Verified per-token prices, GPU amortization, electricity and the break-even point, calculated with real numbers.
Questions people really ask
First: where are you starting from?
No need to be precise: an honest guess is enough.
When you're ready: the setup
The setup planner tells you what hardware you need for the model you want, with the numbers to prove it.
Stay updated
One email a week: local AI news, new models and tutorials. No spam, unsubscribe whenever you want.