← Blog

Edge AI

AI

/dictionary/edge-ai

Definition

Running model inference on the device the data is captured on (phone, camera, sensor) rather than sending it to a server. Models are usually quantized and under 500M parameters. Latency is 5-50ms because there is no network in the loop. Powers Face ID, on-device speech recognition, doorbell person detection.

Related terms

Posts that use this term

  • What leaves your machine when you use AI

    What providers actually see, log, and keep when you call an LLM API in 2026. What "we don't train on your data" really means, how free and paid tiers differ, and when local is the only safe choice.

  • What it takes to run a model on your own machine

    Why VRAM is the one number that decides whether a local LLM runs, what quantization really does to a model file, and the hardware ladder from an 8GB laptop to a 192GB workstation.

  • The major LLMs in 2026

    A field guide to the closed frontier models and the open weights you can actually run. What the "B" numbers mean, and which size fits your machine.

  • Where AI actually runs: cloud, local, edge

    When you use AI, a model file is sitting on a real machine. There are only three places it can be, and which one decides almost everything else.