En
Off‑board tasks with on‑board RAM
With 8GB of dedicated on‑board RAM, the AI HAT+ 2 is ideal for running large language models (LLMs) and vision-language models (VLMs) locally and securely, leaving the host Raspberry Pi 5 free to handle other tasks and ensuring your AI models run smoothly.
A model for privacy and security
Delivering reliable, low-latency AI processing at the edge and without a network connection, the AI HAT+ 2 simplifies data security, minimises infrastructure requirements, and reduces cloud API costs.
Ready-made models
A set of sample models is provided by Hailo; users can also train custom vision models or fine-tune generative AI models to suit their application, such as speech to text, translation, or visual scene analysis.
All of the software for compatible generative AI models can be found in Hailo’s GitHub repo.
Compliance
Raspberry Pi AI HAT+ 2 has undergone extensive compliance testing and meets a number of regional and international standards.
View and download relevant certificates and conformity documents.
Obsolescence
Raspberry Pi AI HAT+ 2 will remain in production until at least January 2036.
