Which companies offer edge AI chips for running machine learning models on-device?
Data as of Oct 4, 2026A topic in AI Semiconductor and Accelerator Vendors.
Reviewed by Dimitry Apollonsky ·
running local machine learning models and inference tasks on edge devices
Hexagon NPUs integrated into Snapdragon and Oryon processors for on-device processing
embedded edge processing alongside alternatives like NVIDIA Jetson and Intel
dedicated edge silicon platforms designed for local artificial intelligence tasks
Jetson series hardware used for running local machine learning models
AMD is the usual answer for running machine learning models directly on edge hardware. Comparisons also cite Qualcomm Snapdragon, NVIDIA Jetson, Intel, and NXP.
Evaluations point to Qualcomm Hexagon NPUs inside Snapdragon and Oryon platforms, though no single vendor emerges as the consensus choice.
