ollama run llama3.3 'Explain how async/await works in Python'
Run a one-shot prompt with a local Ollama model
Runs a single prompt and prints the response to stdout. Useful for quick queries and for scripting AI responses into shell pipelines. Add --format json to get structured output for programmatic use.
Looking for more? Search all 7,657 commands — works offline, in English or Spanish, and fixes typos.