MLOps & Infrastructure · intermediate · concept 203 of 311 · Updated Nov 4, 2026
Edge AI & On-Device ML
Running AI models directly on devices (phones, IoT, cars) instead of in the cloud. Enables low-latency, privacy-preserving AI. Requires model compression and optimization.
Top AI contributors on this
- Jensen HuangNvidia
- Rene HaasArm / SoftBank Group International
- Bill DallyNVIDIA
- Amnon ShashuaMobileye / Hebrew University of Jerusalem
Key terms
LiteRT (formerly TensorFlow Lite)CoreMLONNXEdge TPUModel optimizationOn-device NPUs
Learn these first
Where you meet it in the real world
Smartphone cameras, smart speakers, autonomous vehicles, industrial IoT
Videos
▶ What is edge computing? ↗
IBM Technology · YouTube
Guides and articles
Courses, papers, and more
This unlocks