Install Ollama from the official website or package manager
Open a terminal or command prompt
Verify installation with `ollama –version`
Download a model with `ollama pull
Run a model with `ollama run
Type prompts directly into the chat session
Exit the session with `Ctrl+C` or `/bye` if available
List installed models with `ollama list`
Remove a model with `ollama rm
Start the Ollama server with `ollama serve` if needed
Use the API at `http://localhost:11434`
Send requests to the API with your preferred tool or code
Create a custom model with a `Modelfile`
Build the custom model with `ollama create
Share or reuse models by pulling them on another machine