AI Accelerator · serves as: AI Inference, Computer vision processing.
Which group Hailo-8L M.2 belongs to and how it is built
Covers integrated System-on-Chip circuits used as central processing units in embedded systems, robotics, AIoT, and edge AI devices. In this schema, parentCategory is set to 'other' because the parentCategory enum does not include a compute category.
An AI Accelerator is a specialized hardware component designed for efficient execution of artificial intelligence computations, particularly neural network inference, computer vision processing, and sensor data analysis. In robotics, AI accelerators are used to run perception models, object recognition, image segmentation, planning, and other tasks that require high computational throughput under constrained power budgets. They may take the form of dedicated NPU, TPU, VPU, or GPU chips, or specialized embedded modules.
INT8; Hailo-8 (full version) = 26 TOPS
No external DRAM — on-chip SRAM only
Hailo-8L M.2 is an M.2 form-factor AI accelerator module featuring the Hailo-8L chip (13 TOPS). It is distinguished by typical 1.5 W power draw and a dataflow architecture with no external DRAM (only ~25 MB on-chip SRAM), drastically reducing energy consumption. PCIe Gen3 ×2 interface. Manufactured in TSMC 16nm FinFET. It is the official component in the Raspberry Pi AI HAT+ (13 TOPS version). Supported by HailoRT and the Hailo Dataflow Compiler. The Model Zoo includes 100+ compiled networks (YOLO, ResNet, EfficientDet, BERT-lite).
