Local AI
The pack is not unlocked yet. Sign up below and click the link in the confirmation email – that link opens it. Jump to the practice pack ↓
You are subscribed, but this browser does not carry the access. Open the link from your welcome email here once more. Jump to the practice pack ↓
A model running on your machine costs nothing per request, works without a network and sends no data away – if you set it up properly. This path first settles when that pays off and what “open” means for models. Then it gets practical: start the first model, work out the memory it needs, put hardware promises in perspective and combine local and cloud so that every task lands where it belongs.
- 7
- 71
- For anyone who wants to keep data in-house or bring running costs down.
- Ollama
- LM Studio
- Quantisation
- Hardware
- Routing
0 of 7 stations · 0 of 71 min
Your progress lives in this browser. No account, no data with us.
- Local AI vs. Cloud: When Your Own Models Pay Off
You can justify for a concrete use whether local, cloud or both is the right choice.
- Open-Weight Models: What “Open” Really Means in AI
You read a model licence and know whether you may use the model commercially.
- Running a local model
You start a model on your machine and talk to it via chat and through the local interface.
- Doing the memory maths: does the model fit?
You estimate before downloading whether a model fits your hardware – from parameters, quantisation and context.
- AI PCs and NPUs: What's Really Behind the Marketing
You can tell what an “AI PC” actually does for local models – and what is only on the sticker.
- LM Studio Bionic. How local is your agent?
For a local agent, you check where the model really computes and which tools carry data outside.
- Combining local and cloud
You split tasks between local model and cloud by confidentiality and difficulty – with a rule you can write down.
Path complete. Every station on this route is lit – the practice pack below turns reading into doing.
Work through it, don't just read it
The practice pack holds one exercise per station, the answers to every self-test and the closing overview. It is free for newsletter subscribers – confirm the newsletter once and it opens.
Double opt-in: you first receive a confirmation email – without your click you are on no list. Unsubscribe using the link in any issue. Details in the privacy policy.
You are subscribed – the pack is open.
Open the practice packAlready subscribed on another device? Open the pack