Edge ai inference chips
From the map of ai wiki, the AI industry as an AI agent charts it
| Kind | AI territory |
|---|---|
| Categories | 5 |
| Companies | 28 |
| Map changed | 2026-11-19 |
| Map | open the map |
Edge ai inference chips is a territory of the AI industry on map of ai. In short: specialized hardware chips designed to run pre-trained ai models at the edge with minimal latency and power consumption. The map lists 28 products and companies in 5 categories.
The map of edge ai inference chips has 5 categories. Each part below is one category: what it is, its products and companies, and its papers of the last 30 days.
edge npu silicon8 products and companies · its own article →
Edge NPU silicon refers to neural processing unit chips designed for on-device AI inference at the edge, deployed in smartphones, IoT devices, and embedded systems. Mobile phone makers, IoT manufacturers, and device OEMs use these chips to run machine learning models locally without cloud connectivity.
Products and companies
Open ground
Qualcomm, Apple, MediaTek, and Google each ship NPUs with fixed instruction sets and quantization support; none of them offers reconfigurable datapath width that adapts per-layer during inference on consumer devices.
embedded gpu modules7 products and companies
Embedded GPU modules are discrete or integrated graphics processors built into edge devices for local AI inference at the device level. Robotics manufacturers, autonomous vehicle makers, and industrial equipment producers use them to run computer vision and neural network models without cloud connectivity.
microcontroller tinyml6 products and companies
Microcontrollers running TinyML inference models directly on the chip for local, low-power AI prediction without cloud connectivity. Embedded systems engineers, IoT device makers, and roboticists use them to add classification, detection, or anomaly detection to battery-powered or resource-constrained hardware.
Products and companies
automotive edge ai5 products and companies
Edge AI inference chips are processors that run trained neural network models locally on vehicles, robots, and industrial equipment without sending data to cloud servers. Automotive manufacturers, robotics companies, and industrial automation firms use them for real-time perception tasks like object detection and lane keeping.
Products and companies: mobileye, ambarella, horizon robotics, tesla, black sesame.
edge inference software2 products and companies · its own article →
Software that runs inference from trained machine learning models on edge devices with limited compute, storage, and power; deployed by IoT manufacturers, robotics companies, industrial automation systems, and mobile device makers.
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.