on-device
On-device refers to running computation, such as an AI model, directly on a user's device rather than on cloud servers.
On-device describes processing data and running AI models on a user's own hardware, such as a smartphone, PC, or web browser. It contrasts with cloud processing, in which data is sent to servers.
Because data stays on the device, the approach favors privacy, avoids network round trips that add latency, and incurs no server inference costs. Limited compute and memory on devices mean it typically relies on smaller models.
This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.
Articles covering this entry
▲ Offline on-device AI
The on-device version is a compressed variant that runs on the robot itself, which removes network round trips and keeps the robot working where bandwidth is po…
An on-device model checks that buffer for acoustic patterns such as alarms or speech.