# 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

[Llama 4 Scout  
Natively multimodal model that offers single H100 GPU efficiency and a 10M context window  
Learn more](/content/docs/model-cards-and-prompt-formats/llama4/index.html)

[Llama 4 Maverick  
Natively multimodal model for image and text understanding and fast responses at a low cost  
Learn more](/content/docs/model-cards-and-prompt-formats/llama4/index.html)

[Llama Guard 4  
Updated protection models with higher performance and support for Llama 4  
Learn more](/content/docs/model-cards-and-prompt-formats/llama-guard-4/index.html)

# Get the models

You can obtain the models directly from Meta or from one of our partners, [Hugging Face](https://huggingface.co/meta-llama), [Kaggle](https://www.kaggle.com/organizations/metaresearch/models) or from our [Edge partners](/content/docs/getting-the-models/1b3b-partners/index.html) or [Cloud partners](/content/docs/getting-the-models/405b-partners/index.html).

[Download models](/content/llama-downloads/index.html)

## 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](https://github.com/meta-llama/llama-models/blob/main/models/llama4/MODEL_CARD.md)

### Prompt Format

How to construct effective prompts.

[Get prompt guidance](/content/docs/model-cards-and-prompt-formats/llama4/index.html)

### Get the model

Direct or through a partner.

[Download](/content/llama-downloads/index.html) [Hugging Face](https://huggingface.co/meta-llama)

## 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](https://github.com/meta-llama/llama-models/blob/main/models/llama4/MODEL_CARD.md)

### Prompt Format

How to construct effective prompts.

[Get prompt guidance](/content/docs/model-cards-and-prompt-formats/llama4/index.html)

### Get the model

Direct or through a partner.

[Download](/content/llama-downloads/index.html) [Hugging Face](https://huggingface.co/meta-llama)

## 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](https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Guard4/12B/MODEL_CARD.md)

### Prompt Format

How to construct effective prompts.

[Get prompt guidance](/content/docs/model-cards-and-prompt-formats/llama-guard-4/index.html)

### Get the model

Direct or through a partner.

[Download](/content/llama-downloads/index.html) [Hugging Face](https://huggingface.co/meta-llama)

## Find us on GitHub

[Llama cookbookNotebooks and demos for learning Llama. Scripts for fine-tuning Llama3 with single/multi-node GPUs.  
Learn more](https://github.com/meta-llama/llama-cookbook)

[Llama StackDefines and standardizes the building blocks needed to bring generative AI applications to market.  
Learn more](https://github.com/llamastack/llama-stack)

## Other topics in this guide

[Getting Llama modelsTry out Llama models today.  
Learn more](/content/docs/getting-the-models/index.html)

[How-to guidesAn overview of the processes for developing any LLM: fine-tuning, prompt engineering, and model validation.  
Learn more](/content/docs/how-to-guides/index.html)

[Integration guidesDevelop solutions based on Code Llama, LangChain, and LlamaIndex.  
Learn more](/content/docs/integration-guides/index.html)

[Community supportCompilation of resources available from the community.  
Learn more](/content/docs/community-support-and-resources/index.html)