With Ollama, you can easily browse, download, and test a variety of open-source language models right on your local machine. This guide walks you through the basic workflow for downloading and running a text-based model.
Step 1 : Find a Model
Browse the Ollama model library and choose a model you want to try. Take note of the model name (for example, mistral or codellama).
Step 2 : Download the Model
To download a model, use the ollama pull command:
The download may take a few minutes, depending on the model size and your internet speed.
Step 3 : Verify Downloaded Models
Once the download finishes, list all locally available models with:
You'll see the model name, size, and last modified time.
Step 4 : Run and Test the Model
To start an interactive chat session, run:
You can now type questions (e.g., “Write a Python function that returns 'hello world'”) and the model will generate responses directly in your terminal.
Step 5 : End the Session
To exit the chat session, type /bye or press Ctrl+d.
Step 6 : Remove a Model
If you want to free up space, remove a model you no longer need:
That's it! You're ready to explore and test language models with Ollama on your own machine.