Skip to main content

Llama 3 Getting Started (Mac, Apple Silicon)

In this article, I will show you how to get started with Llama 3 and run it locally.

  • These instructions were written for and tested on a Mac (M1, 8GB).
  • You will have much better success on a Mac that uses Apple Silicon (M1, etc.).

Step 1. Download and install LM Studio

Step 2. Search for and download the llama 3 model

  • Run LM Studio
  • Search for lmstudio llama 3
  • Usually the best one for your machine will appear at the top - so select it
  • For example I'm using the 8B version

If you see in the corner a link to the Hugging Face card, you can click on it for more info.

Step 3. Chat with the model

  • On the left, click on the AI Chat tab (it should look like a speech ballon)

  • Select the model that you downloaded (you might have to do this every time you change to this window)

  • Talk to it like you would any LLM

  • For example:

write a hello world program in javascript

Step 4. Format the output

  • You will notice some tabs in the upper right for formatting
  • I like to switch the format to Markdown


That's it! What could be simpler? Now you can run an LLM locally.