# www.llama.com

> AI-optimized mirror of www.llama.com containing 51 pages totalling 38,426 words of clean markdown content, structured data, and semantic HTML. Original source: https://www.llama.com/. Last updated: 2026-05-17T19:29:26.778Z.

Each page is available as HTML (with JSON-LD structured data) and Markdown (text-only, ideal for LLMs and RAG).

## Homepage

- [Build on your own terms](/site-root.html): Discover Llama 4's class-leading AI models, Scout and Maverick. Experience top performance, multimodality, low costs, and unparalleled efficiency. (1,085 words)

## Articles & Blog Posts

- [How to fine-tune Llama models for structured extraction of data from images](/resources/videos/llama-fine-tune-structured-image-extraction/index.html): Learn how to customize Llama for your use case. (407 words)
- [Developer use guide resources](/docs/how-to-guides/responsible-use-guide-resources/index.html): We are committed to supporting our community in building Llama applications responsibly. As part of that commitment, we provide this Developer Use Guide that outlines best practices in the context of Responsible GenAI. (1,055 words)
- [Helping Upwork freelancers win more business with Llama](/resources/case-studies/upwork/index.html): Helping Upwork freelancers win more business with Llama (966 words)
- [Getting the models](/docs/getting-the-models/meta/index.html): You can get the Meta Llama models directly from Meta or through Hugging Face or Kaggle. (324 words)
- [Getting the models](/docs/getting-the-models/kaggle/index.html): To obtain the models from Kaggle–including the HF versions of the models–sign into your account at kaggle.com/organizations/metaresearch/models. (277 words)
- [Introduction](/docs/model-cards-and-prompt-formats/llama-guard-4/index.html): Llama Guard 4 builds on the capabilities introduced in Llama Guard 3 and supports both the Llama 4 and Llama 3 model lines. (1,756 words)
- [docs/how-to-guides/evaluations/index.html](/docs/how-to-guides/evaluations/index.html) (1 words)
- [docs/how-to-guides/quantization/index.html](/docs/how-to-guides/quantization/index.html) (1 words)
- [Get updates about Llama](/subscribe/index.html): Subscribe to get the latest updates from Llama, plus the latest AI news, breakthroughs and upcoming events from Meta in our newsletter. (210 words)
- [Troubleshooting & FAQ](/faq/index.html): Llama — The next generation of our open source large language model, available for free for research and commercial use. (2,556 words)
- [Llama 3.3](/docs/model-cards-and-prompt-formats/llama3_3/index.html): . (852 words)
- [Unifying internal knowledge for faster insights and efficiency](/resources/case-studies/stoque/index.html): Transforming internal intelligence with Llama. Stoque enabled teams to find insights faster, reduce friction, and work more efficiently at scale. (776 words)
- [Deployment](/docs/deployment/index.html): Explore Llama's full potential with our comprehensive documentation and resources. Drive developer productivity and innovation. (761 words)
- [Llama videos](/resources/videos/index.html): Explore the world of open-source AI with Llama models and products through educational videos, tutorials, and expert discussions. (356 words)
- [Unlocking economic impact through open source AI](/llama-ai-innovation/index.html): Discover how open source AI is revolutionizing industries, fostering economic growth, and creating opportunities for innovation and entrepreneurship. (2,531 words)
- [Llama cookbook and tools](/resources/cookbook/index.html): Get instant access to expert-led guides, code snippets, and community-driven resources to supercharge your development workflow. (581 words)
- [Enabling AI Defenders](/llama-protections/ai-defenders/index.html): Join Meta's Llama Defenders Program to access cutting-edge tools and benchmarks designed to safeguard organizations against AI-enabled threats and enhance cybersecurity. (786 words)
- [How to build your own multi-modal WhatsApp chatbot with Llama 4](/resources/videos/build-multi-modal-whatsapp-chatbot-with-llama-4/index.html): Build an intelligent chatbot for your business on WhatsApp. (446 words)
- [Get started with Llama](/docs/overview/index.html): Explore Llama's full potential with our comprehensive documentation and resources. Drive developer productivity and innovation. (447 words)
- [Developer Use Guide](/developer-use-guide/index.html): The Developer Use Guide is a resource for developers that provides best practices and considerations for building products powered by large language models (LLM) in a responsible manner, covering various stages of development from inception to deployment. (371 words)
- [Case studies](/resources/case-studies/index.html): Llama case studies (244 words)
- [How-to guides](/docs/how-to-guides/index.html): Explore Llama's full potential with our comprehensive documentation and resources. Drive developer productivity and innovation. (509 words)
- [Llama API](/products/llama-api/index.html): Build fast and secure AI projects with Llama API, offering lightweight SDKs and compatibility with OpenAI. Sign up for limited preview today! (432 words)
- [Llama Models](/docs/model-cards-and-prompt-formats/index.html): To correctly prompt each Llama model, please closely follow the formats described in the following sections. (410 words)
- [Open Innovation AI Research Community](/open-innovation-ai-research-community/index.html): We’re launching a program for academic researchers, designed to foster collaboration and knowledge-sharing in the field of artificial intelligence. (558 words)
- [Integration guides](/docs/integration-guides/index.html): . (164 words)
- [Llama Protections](/llama-protections/index.html): Llama Protections models and tools embrace both offensive and defensive strategies. (1,086 words)
- [docs/model-cards-and-prompt-formats/llama3_2/index.html](/docs/model-cards-and-prompt-formats/llama3_2/index.html) (1 words)
- [docs/model-cards-and-prompt-formats/llama3_1/index.html](/docs/model-cards-and-prompt-formats/llama3_1/index.html) (1 words)
- [docs/how-to-guides/vision-capabilities/index.html](/docs/how-to-guides/vision-capabilities/index.html) (1 words)
- [docs/how-to-guides/prompting/index.html](/docs/how-to-guides/prompting/index.html) (1 words)
- [docs/how-to-guides/fine-tuning/index.html](/docs/how-to-guides/fine-tuning/index.html) (1 words)
- [Oxen.ai](/resources/case-studies/oxen-ai/index.html): Accelerating the fine-tuning process with more control over model weights (1,067 words)
- [community-stories/index.html](/community-stories/index.html) (1 words)
- [Llama 4](/docs/model-cards-and-prompt-formats/llama4/index.html): Technical details and prompt guidance for Llama 4 Maverick and Llama 4 Scout (2,615 words)
- [Llama 3.2 Community License Agreement](/llama3_2/license/index.html): Llama 3.2 Community License Agreement (1,259 words)
- [Distillation](/docs/how-to-guides/distillation/index.html): Learn how to distill a large language model into a smaller one using synthetic data generation and fine-tuning, and evaluate the distilled model's performance and efficiency. Discover techniques for distillation, including hard features, logit targets, and feature targets, to transfer knowledge from a teacher model to a student model. (1,360 words)
- [Community License Agreement](/llama3/license/index.html): Meta Llama 3 License (1,294 words)
- [Running Llama on Mac](/docs/llama-everywhere/running-meta-llama-on-mac/index.html): For this demo, we are using a Macbook Pro running Sonoma 14.4.1 with 64GB memory. Since we will be using Ollamap, this setup can also be used on other operating systems that are supported such as Linux or Windows using similar steps as the ones shown here. (1,215 words)
- [Community License Agreement](/llama3_1/license/index.html): Llama 3.1 Community License Agreement (1,258 words)
- [Community License Agreement](/llama3_3/license/index.html): Llama 3.3 Community License Agreement (1,258 words)
- [Llama 4](/llama4/license/index.html): Llama 4 Community License Agreement (1,258 words)
- [Acceptable Use Policy](/llama3_3/use-policy/index.html): Llama 3.3 Acceptable Use Policy (860 words)
- [Acceptable Use Policy](/llama3_2/use-policy/index.html): Llama 3.2 Acceptable Use Policy (838 words)
- [Llama 4](/models/llama-4/index.html): Meet Llama 4, the latest multimodal AI model offering cost efficiency, 10M context window and easy deployment. Start building advanced personalized experiences. (466 words)
- [Llama 3](/models/llama-3/index.html): Discover Llama 3's open-source AI models you can fine-tune, distill and deploy anywhere. Build smarter applications with flexible AI solutions. (517 words)
- [Llama 3](/docs/model-cards-and-prompt-formats/meta-llama-3/index.html): Special Tokens used with Llama 3. A prompt should contain a single system message, can contain multiple alternating user and assistant messages, and always ends with the last user message followed by the assistant header. (545 words)
- [Acceptable Use Policy](/llama3_1/use-policy/index.html): Llama 3.1 Acceptable Use Policy (706 words)
- [Llama Startup Program](/programs/startups/index.html): Discover the Llama Startup Program, designed to help early-stage startups innovate and grow faster. Sign up to receive updates and be notified when applications open. (524 words)
- [Request Access to Llama Models](/llama-downloads/index.html): Request access to Llama. (1,432 words)

## Resources

- [Full Page Index](/index.html): Browse all cached pages with rich metadata
- [About This Cache](/content/about.html): Methodology, technical details, and usage guidelines
- [XML Sitemap](/content/sitemap.xml): Machine-readable sitemap for crawler discovery
- [Robots.txt](/content/robots.txt): Crawler directives