Llama 3.2 includes small and medium-sized vision LLMs and lightweight, text-only models that can be used on edge and mobile devices, offering improved performance, efficiency, and safety.
Llama 3.2 supports vision tasks, including image reasoning and visual understanding.
Llama 3.2 can be used on edge and mobile devices, making it a powerful tool for developers.
Llama 3.2 offers improved performance and efficiency, making it a powerful tool for developers.
Llama 3.2 includes safety and security features, such as Llama Guard, to ensure responsible use.
Llama 3.2 includes the Llama Stack API, a standardized interface for building and customizing Llama models.
Image recognition and classification
Visual understanding and reasoning
Edge and mobile device applications
Improved performance and efficiency
Safety and security features
Download Llama 3.2 models on llama.com and Hugging Face
Start building with Llama 3.2 using the Llama Stack API
Use Llama 3.2 on edge and mobile devices
Integrate Llama 3.2 with other tools and services
Explore safety and security features, such as Llama Guard