Hello Hailo Community!
We are thrilled to announce the next leap for Hailo on Raspberry Pi: the AI HAT+ 2. While the original AI HAT brought world-class vision to the Pi 5, the AI HAT+ 2 is designed to bring Generative AI to the edge.
Key Highlights:
- Hailo-10H Powered: Delivers a massive 40 TOPS (INT4) of AI performance.
- 8GB Onboard RAM: Dedicated LPDDR4X memory allows you to run LLMs without taxing the Pi’s system memory.
- GenAI Ready: Locally run small LLMs and VLMs like Llama 3 and Qwen2.5 or larger Whisper with high efficiency and low latency.
- Plug & Play: Fully compatible with Raspberry Pi 5 and the standard
hailo-appsandrpicam-appsstacks. - Built-in Ollama integration
Why Upgrade?
The Raspberry Pi AI HAT+ 2 is designed for on-device AI workloads, in cases where low power, low latency, and privacy are important. It’s best fit for use cases like VLMs for event triggering, logging, indexing, captioning, and smart search using free text. One exciting type of application is voice-to-action, where LLMs are used to bridge the gap between human intent and tools execution.
The Raspberry Pi AI HAT+ 2 was not designed to be a replacement for cloud inference or large LLMs, but a strong fit for physical and agentic AI at the edge, especially in home automation, security, robotics, and industrial applications.
Check out our GitHub for updated Hailo-10H Compiled model files, hailo-ollama integration, and example applications.
Watch our product introduction video for some use-case ideas.
We can’t wait to see your benchmarks and projects!
Best, The Hailo Team
