Ollama
Local runtime that downloads, quantises and runs open-weight language models, exposing them over its own HTTP API and an OpenAI-compatible endpoint. Also serves embedding models.
The simplest possible setup for chatting with local AI models. This combo pairs Ollama's local LLM inference with Open WebUI's clean chat interface, creating a completely private ChatGPT-like experience that runs entirely on your machine. Ollama handles downloading and running models like Llama or Mistral, while Open WebUI provides the familiar conversational interface you're used to from cloud AI services. Perfect for getting started with local AI without any complexity - just download a model and start chatting.