Hailo Announces Commercial Availability of Hailo-10H Edge AI Accelerator with Generative AI Capabilities
July 30, 2025
News
Hailo announced the commercial availability of the Hailo-10H, its second-generation AI accelerator featuring generative AI capabilities. Per the company, customers worldwide can now download the software from Hailo’s website and place orders for the Hailo-10H, the first market-available and orderable discrete AI processor with native support for generative AI workloads at the edge.
Building on the company’s first-generation AI accelerator, Hailo-8, the Hailo-10H is designed to complement vision AI tasks with new generative AI capabilities and introduce, for the first time, the ability to run large language models (LLMs), vision-language models (VLMs), and other generative AI models entirely on-device, without relying on cloud connectivity.
The Hailo-10H features an M.2 Key M (2242, 2280) form factor, PCIe Gen-3.0, 4-lanes (x4) interface, support for TensorFlow, TensorFlow Lite, Keras, PyTorch & ONNX AI frameworks, on-module 4|8GB LPDDR4/4X, support for x86 or ARM host architectures, and supoort for Linux, Windows, and Android OS.
This upgrade is designed to bring generative AI to edge devices with cost and power efficiency, making the Hailo-10H a solution for product developers across multiple sectors, including personal compute, automotive, telecommunication, retail, security, and more.
The Hailo-10H is fully compatible with Hailo’s software stack and benefits from the support of a global developer community with more than 10,000 users each month. It empowers developers to run vision and generative AI models directly on edge devices, delivering real-time responsiveness with ultra-low latency.
By processing data locally, the Hailo-10H ensures strong data privacy, since personally identifiable information remains on the device, while reducing overall system costs by minimizing both cloud bandwidth usage and the need for expensive cloud-based AI service subscriptions. Additionally, the AI operates independently of cloud connectivity, ensuring consistent availability even in environments with limited or no internet access.
Specifically designed for edge devices across consumer, enterprise, and automotive markets, including media centers, home gateways, and automotive cockpit systems, the Hailo-10H is designed to enable advanced use cases like natural language human-machine interaction, visual awareness, and multi-modal AI to run seamlessly within the power and cost constraints typical of edge environments.
Per the company, in performance benchmarks, the Hailo-10H has demonstrated unique results across generative workloads. For example, achieving a first-token latency of under 1 second and over 10 Tokens per Second on a variety of 2B language and vision-language models. For video analytics, the Hailo-10H enables 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 ideal for compact, efficient AI-enabled systems.
The Hailo-10H is automotive-qualified to AEC-Q100 Grade 2 standards and is aimed at automotive designs with a 2026 start of production.
For more information, visit: https://hailo.ai/products/ai-accelerators/hailo-10h-m-2-ai-acceleration-module/#hailo10m2-overview
Tiera Oliver, Assistant Managing Editor for Embedded Computing Design, is responsible for web content edits, product news, and constructing stories. She develops content and constructs ECD podcasts, such as Embedded Insiders. Before working at ECD, Tiera graduated from Northern Arizona University, where she received her B.S. in journalism and political science and worked as a news reporter for the university’s student-led newspaper, The Lumberjack.
