Experience an interactive LLM chat demo – your familiar ChatGPT-style conversation, now running entirely on the edge, powered entirely by the Hailo-10H AI accelerator, with no internet connection required.
Perfect for fast, responsive, on-device AI applications, this demo showcases local inference in action using the Ollama user interface.
Powered by the Hailo SDK, it’s fully compatible with both Ollama and OpenAI REST APIs, enabling easy development and a seamless user experience across platforms.
