Ollama is a powerful tool that allows you to run large language models locally on your Mac. This guide will walk you through the steps to install and run Ollama on macOS.
Prerequisites
A Mac running macOS 11 Big Sur or later
An internet connection to download the necessary files
Step 1: Download Ollama
Click on the Download for macOS button.
Once the download is complete, locate the .zip file in your ~/Downloads folder.
Double-click the .zip file to extract its contents. This should create Ollama.app.
Step 2: Install Ollama
Drag Ollama.app to your Applications folder.
Open the Applications folder and double-click on Ollama.app.
If you see a warning, click Open to proceed.
Follow the setup wizard to complete the installation. The wizard will prompt you to install the command line version (ollama).
Step 3: Running a Model
Open the Terminal application.
To run the Llama 3 model, type the following command and press Enter: ollama run llama3
The first time you run this command, it will download the latest version of the model. This may take some time depending on your internet speed.
Step 4: Interacting with the Model
Once the model is downloaded, you will see a prompt like this:>>> Send a message (/? for help)
Start chatting with the model by typing your messages at the prompt.
Step 5: Getting Help
To get help at the prompt, type /? and press Enter.
To get help from the command line interface, simply run the command without any arguments: ollama
Step 6: Managing Models
To see a list of currently installed models, run: ollama list
To remove a model and free up disk space, run: ollama rm llama3
If you want to know how to run Llama 3.2 using Ollama on MacOS, click here: https://www.metriccoders.com/post/run-llama-3-2-on-ollama-in-macos
If you are looking to run DeepSeek R1 on Ollama on MacOS, click here: https://www.metriccoders.com/post/run-deepseek-r1-on-ollama
Conclusion
By following these steps, you should be able to install and run Ollama on your Mac, allowing you to leverage the power of large language models locally.