Mountain Camp 2027

A Practical Guide to Fast and Private LLMs

Want to run your own AI, at home or at work? This talk shows you how. You'll learn how to pick the right model, make it run faster and more efficient, choose the hardware, and set up the software. A quick tour of running your own LLMs for fun and for real work.


Most AI tools send your text to someone else's servers. You don't have to work that way. If you run a model yourself, your data stays with you, your costs stay clear, and you use less power than most people expect.

This talk shows you how to do it. We walk through the choices that actually matter: which model size fits your job, how to shrink and speed it up, what hardware you need (and what you can skip), and which software to run it on. Everything comes from real setups, not theory.

You'll leave knowing enough to build your own private AI, as a weekend project or as something your team can rely on.

Lena Fuhrimann

I love cloud-native and serverless software engineering using AI that keeps me digitally independent.

I work as an engineer with Kubernetes, AWS, and Azure. As such, I do a lot of development using languages like Go, TypeScript or Python. Modern software engineering needs to be cloud-native or even serverless.

I've worked with more than 100 customers to migrate their products and applications to the cloud.