Edge AI accelerator with generative AI capabilities available now

Hailo has announced the commercial availability of the Hailo-10H, its second-generation AI accelerator featuring powerful generative AI capabilities. Customers worldwide can download the software from the company's website and place orders for the Hailo-10H, marking the highly anticipated arrival of the first market-available and orderable discrete AI processor with native support for generative AI workloads at the edge.

Building on the proven success of its first-generation AI accelerator, Hailo-8, the new device complements the industry-leading performance in vision AI tasks with new generative AI capabilities. It introduces, for the first time, the ability to run LLMs, VLMs, and other generative AI models completely on-device, without relying on cloud connectivity. This leap in functionality brings powerful generative AI to edge devices with unmatched cost and power efficiency, making the device a game-changing solution for product developers across multiple sectors, including personal compute, automotive, telecommunication, retail, security and more.

"With the Hailo-10H now available for order, we're taking another major step toward our mission of making AI accessible to all," said Orr Danon, CEO and co-founder of Hailo. "This is the first discrete AI processor to bring real generative AI performance to the edge, combining high efficiency, cost-effectiveness, and a robust software ecosystem."

The accelerator is fully compatible with the company's mature and widely adopted software stack and benefits from the support of a vibrant global developer community with more than 10,000 users each month. It empowers developers to run state-of-the-art vision and generative AI models directly on edge devices, providing real-time responsiveness with ultra-low latency.

By processing data locally, the device ensures strong data privacy, since personally identifiable information remains on the device, while significantly reducing overall system costs by minimising cloud bandwidth usage and the necessity for expensive cloud-based AI service subscriptions. Just as importantly, the AI operates independently of cloud connectivity, providing consistent availability even in environments with limited or no internet access.

Specifically designed for edge devices across consumer, enterprise, and automotive markets, including media centres, home gateways, and automotive cockpit systems, the Hailo-10H enables advanced use cases such as natural language human-machine interaction, visual awareness, and multimodal AI to run seamlessly within the power and cost constraints typical of edge environments.

In performance benchmarks, the Hailo-10H has demonstrated outstanding results across generative workloads. For example, achieving a first-token latency of under one second and over ten tokens per second on a variety of 2B language and vision-language models. For video analytics, it enables state-of-the-art object detection (e.g., YOLOv11m) on a real-time 4K video stream. All of these come at a typical power consumption of just 2.5W, making it excellent for compact, efficient AI-enabled systems. The Hailo-10H is automotive-qualified to AEC-Q100 Grade 2 standards and is designed for automotive applications with a 2026 start of production.