Meta
Search
Home
Get started
Overview
Models
Overview
Llama 4
Llama Guard 4
Llama 3.3
Other models
Use our models
Cloud partners
Edge partners
Download
Meta
Hugging Face
Kaggle
Building with Llama
How to guides
Overview
Prompt Engineering (Updated)
Fine-tuning
Quantization
Distillation
Validation
Vision Capabilities
Responsible Use
Integration guides
Overview
LangChain Integration
LlamaIndex Integration
Deployment guides
Overview
Private cloud
Production pipelines
Infrastructure migration
Versioning
Accelerator management
Autoscaling
Regulated industry self-hosting
Security in production
Cost projection and optimization
Comparing costs
Llama DocumentationGet startedOverview
Stay updated
Get started
Meta
post image
post image
post image
post image
Products
Muse Code
Meta Model API
Models
Muse Spark 1.2
Muse Spark 1.1
Muse Glimmer
Llama 4
Llama 3
Documentation
Meta Model API Docs
Muse Glimmer Docs
Llama Docs
Resources
Cookbook
Blog
Videos
Case studies
FAQs
Community
Meta-Models Github
Llama GitHub
Hugging Face
Terms & policies
Terms of Service
Privacy Policy
Cookie Policy
Products
Muse Code
Meta Model API
Models
Muse Spark 1.2
Muse Spark 1.1
Muse Glimmer
Llama 4
Llama 3
Documentation
Meta Model API Docs
Muse Glimmer Docs
Llama Docs
Resources
Cookbook
Blog
Videos
Case studies
FAQs
Community
Meta-Models Github
Llama GitHub
Hugging Face
Terms & policies
Terms of Service
Privacy Policy
Cookie Policy
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

Muse Spark
Muse Spark writes, reviews and ships code with fewer steps and lower latency
Learn more
Llama 4 Scout
Natively multimodal model that offers single H100 GPU efficiency and a 10M context window
Learn more
Llama 4 Maverick
Natively multimodal model for image and text understanding and fast responses at a low cost
Learn more

Get the models

You can obtain the models directly from Meta or from one of our partners, Hugging Face, Kaggle or from our Edge partners or Cloud partners.
Download models

Llama 4 Scout

Natively multimodal model that offers single H100 GPU efficiency and a 10M context window
Model Card
Model attributes in easy to consume, standard format.
View on Github
Prompt Format
How to construct effective prompts.
Get prompt guidance
Get the model
Direct or through a partner.
Download
Hugging Face

Llama 4 Maverick

Natively multimodal model for image and text understanding and fast responses at a low cost
Model Card
Model attributes in easy to consume, standard format.
View on Github
Prompt Format
How to construct effective prompts.
Get prompt guidance
Get the model
Direct or through a partner.
Download
Hugging Face

Llama Guard 4

Updated protection models with higher performance and support for Llama 4
Model Card
Model attributes in easy to consume, standard format.
View on Github
Prompt Format
How to construct effective prompts.
Get prompt guidance
Get the model
Direct or through a partner.
Download
Hugging Face

Find us on GitHub

Llama cookbookNotebooks and demos for learning Llama. Scripts for fine-tuning Llama3 with single/multi-node GPUs.
Learn more
Prompt OpsAn open-source tool for LLM prompt optimization.
Learn more

Other topics in this guide

Getting Llama modelsTry out Llama models today.
Learn more
How-to guidesAn overview of the processes for developing any LLM: fine-tuning, prompt engineering, and model validation.
Learn more
Integration guidesDevelop solutions based on Code Llama, LangChain, and LlamaIndex.
Learn more
Community supportCompilation of resources available from the community.
Learn more