Agentic AI Reference Architecture

Infrastructure · Infrastructure resource

Edge NPU Device

Infrastructure resourceInfrastructureInfrastructurearc:EdgeNPUDevice

A smartphone or embedded system with an integrated neural processing unit providing dedicated low-power AI acceleration.

Responsibility. Runs on-device models on integrated neural accelerators.

Also known as: Neural processing unit

Variant of Edge Device abstract

When to choose. Choose for mobile and embedded products where dedicated AI acceleration must consume minimal power.

is target of alternativeTospecializesis target of alternativeToalternative toEdge GPU Device: is target of alternativeToEdge GPU DeviceEdge Device: specializesEdge DeviceEdge FPGA Device: is target of alternativeToEdge FPGA DeviceEdge TPU Device: alternative toEdge TPU Device
Direct neighbourhood (hover for relationship types)

Relationships

alternative to variability

Quantitative guidance

As stated by the sources; verify before use.

Classification

Technologies
Apple Neural EngineQualcomm Hexagon DSPIntel Movidius
Quality attributes
Performance efficiency (ISO/IEC 25010)

Sources

  1. Ch4.3: T. Nguyen, "Container Orchestration and Edge Deployment," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 4.3. ISBN: 9798244538229.