Run local LLMs in under 5 minutes using Nanocl

Nanocl, a lightweight container orchestration platform, enables users to deploy their own private ChatGPT-like service in under five minutes by combining it with Ollama for running large language models locally and Open WebUI for a web interface. The setup process involves installing Docker and Nanocl, then deploying both services through simple configuration files, allowing users to download AI models like gemma2:2b and interact with them through a browser-based chat interface at a local domain.