Documentation
Get started with Llama
This guide provides information and resources to help you set up Llama including how to access the model, hosting, how-to and integration guides. Additionally, you will find supplemental materials to further assist you while building with Llama.
What's new:
Get the models
Llama 4 Scout (New)
Get the Model
Llama 4 Maverick (New)
Get the Model
Find us on GitHub
Llama Cookbook
Notebooks and demos for learning Llama. Scripts for fine-tuning Llama3 with single/multi-node GPUs.
Llama Stack
Defines and standardizes the building blocks needed to bring generative AI applications to market.
Explore the new capabilities of Llama 3.2
The Llama 3.2 lightweight models enable Llama to run on phones, tablets, and edge devices. View the video to see Llama running on phone. To see how this demo was implemented, check out the example code from ExecuTorch.
Other topics in this Guide
To discover more about what's possible with the Llama family of models, explore the topics below.
Llama Everywhere
Notebooks and information on how to run Llama on your local hardware or in the cloud.
