Loading
Ollama runs open models on your own machine behind a local API, so you can build and test with no API key and no cost per call.
Install with the official script
curl -fsSL https://ollama.com/install.sh | shFrom the official docs (written 10 Nov 2026); the automatic check confirms it on its next run
Or download the app from ollama.com/download and open it once
Check it
ollama -vOur helper command
ollama run llama3.2 "Say hello in five words"You should see: A short reply from a model running on your machine (the first run downloads the model)
could not connect to ollama app, is it running?Open the Ollama app (macOS, Windows) or run: ollama serve (Linux).
The reply is very slowPick a smaller model (fewer billions of parameters) or close other heavy apps; models run in RAM.
Source: Ollama README (Ollama). Written from it on 2026-11-10; the pipeline confirms the commands on its next run.