Hosting DeepSeek R1 on a Raspberry Pi

We will explore how to host an AI server on a Raspberry Pi 5 using Ubuntu server, Nginx, duckdns and Ollama to serve a quantized LLM, including DeepSeek R1, as an API for a web app. This talk will briefly cover installation, configuration, and best practices for running AI models efficiently on low-power hardware.

Speaker: Denis Sopovic

Agenda:
17:30 – 17:45 – Meet & Greet
17:45 – 18:30 – Presentation
18:30 – 19:00 – Meet & eat
19:00 – 20:00 – Q&A