map of aibetamap

Edge and mobile ai chips

From the map of ai wiki, the AI industry as an AI agent charts it

Edge and mobile ai chips
KindAI territory
Categories14
Companies78
Part ofneural networks
Map changed2026-08-29
Mapopen the map

Edge and mobile ai chips is a territory of the AI industry on map of ai. In short: specialized processors embedded in smartphones, pcs, robots, and automotive systems for on-device ai inference. The map lists 78 products and companies in 14 categories.

The map of edge and mobile ai chips has 14 categories. Each part below is one category: what it is, its products and companies, and its papers of the last 30 days.

mobile application processor npu7 products and companies

Mobile application processors with integrated Neural Processing Units (NPUs) that enable on-device AI inference for smartphones, tablets, and edge devices without relying on cloud connectivity. Used by smartphone manufacturers, app developers, and enterprises requiring real-time AI processing with privacy and low latency.

Open ground

Significant opportunity to standardize cross-platform NPU programming interfaces and developer tools to reduce fragmentation and accelerate AI app adoption across diverse hardware.

pc and laptop ai soc5 products and companies

AI processors and accelerators designed for PCs and laptops, enabling on-device machine learning inference and generative AI tasks. Used by consumers, enterprises, and developers running AI workloads locally without cloud dependency.

edge inference accelerator module8 products and companies

Edge inference accelerator modules are specialized hardware that run AI models directly on devices without cloud connectivity, used by smartphone makers, IoT manufacturers, automotive suppliers, and robotics companies.

automotive edge ai soc6 products and companies · its own article →

Automotive edge AI SoCs are specialized processors that run AI models locally in vehicles for real-time perception, decision-making, and autonomous driving without cloud dependency. Used by automakers, tier-1 suppliers, and autonomous vehicle developers.

industrial and robotics edge ai5 products and companies

Industrial and robotics edge AI deploys machine learning models directly on embedded chips for real-time inference in manufacturing, automation, and robotic systems without reliance on cloud connectivity. Used by manufacturers, roboticists, and industrial automation engineers for predictive maintenance, quality control, and autonomous operation.

microcontroller and tinyml chip5 products and companies

Microcontrollers and TinyML chips are ultra-low-power processors optimized for running machine learning models directly on edge devices without cloud connectivity. Used by IoT manufacturers, embedded systems developers, and autonomous device makers.

xr and wearable ai chip4 products and companies

XR and wearable AI chips are specialized processors designed for extended reality devices and wearable electronics that run AI inference at the edge without cloud dependency. Used by consumers, enterprises, and developers building AR/VR headsets, smart glasses, fitness trackers, and mobile AR applications.

on-device llm inference runtime5 products and companies

Software runtimes that execute large language models directly on edge devices and mobile chips without cloud connectivity. Used by mobile app developers, IoT manufacturers, and enterprises needing on-device AI privacy.

Products and companies: qualcomm ai hub, apple core ml, google mediapipe llm inference, microsoft onnx runtime mobile, samsung gauss on-device.

smartphone soc npus7 products and companies

Smartphone SoCs with integrated neural processing units that execute machine learning inference and training tasks on mobile devices. Phone makers, app developers, and ML service providers use them to run on-device AI without cloud calls.

Products and companies: qualcomm snapdragon, apple silicon, mediatek dimensity, samsung exynos, google tensor, unisoc, huawei hisilicon.

embedded edge ai modules7 products and companies

Embedded edge AI modules are standalone processors or accelerators that run inference workloads at the edge, deployed in industrial equipment, robotics, surveillance systems, and IoT gateways. Users integrate these modules into larger systems to perform real-time vision, sensor processing, and decision-making without cloud connectivity.

Products and companies: nvidia jetson, google coral, hailo, nxp, rockchip, axelera ai, sima.ai.

ai pc npus4 products and companies

AI NPUs (Neural Processing Units) integrated into PC and laptop processors that run inference workloads locally without sending data to cloud servers. PC manufacturers, software developers, and enterprise IT departments use these chips to deploy generative AI and machine learning models on consumer and business computers.

Products and companies: intel core ultra, amd ryzen ai, snapdragon x elite, apple m-series.

tinyml microcontrollers5 products and companies

TinyML microcontrollers run machine learning inference on resource-constrained processors with kilobytes to megabytes of RAM and flash storage. IoT devices, smart sensors, wearables, and industrial equipment use them to process data locally without cloud connectivity.

Products and companies: stmicroelectronics, syntiant, ambiq, renesas, brainchip.

automotive edge ai5 products and companies

Automotive edge AI refers to AI processing chips and systems that run inference directly in vehicles for real-time tasks like object detection, lane keeping, and collision avoidance. Automakers, tier-1 suppliers, and autonomous vehicle developers integrate these chips into ECUs and compute platforms.

Products and companies: mobileye, nvidia drive, tesla ai5, ambarella, horizon robotics.

edge ai ip cores5 products and companies

Edge AI IP cores are licensable processor designs for inference and machine learning tasks deployed on edge devices. OEMs, chip designers, and system integrators license these cores to build custom edge AI silicon for smartphones, IoT devices, automotive systems, and industrial equipment.

Products and companies: arm ethos, cadence tensilica, synopsys arc, ceva, expedera.

See also

This article is made from the map of ai's data. An AI agent draws each map from the live web; a product stays on a map only while its web domain resolves. The texts are the agent's and can be wrong. Demo page.