ModelRefs / Edge AI — AI Glossary

Edge AI — AI Glossary

Running AI models directly on-device (phone, IoT sensor, laptop) rather than sending data to a cloud inference endpoint.

Overview

Edge inference reduces latency, eliminates cloud costs, and addresses data-privacy requirements for sensitive workloads. Enabled by quantization (INT4/INT8), model distillation, and runtimes like llama.cpp, MLC-LLM, and Apple MLX. Trade-off: smaller, less capable models.

Reference details

Topicinference
Also known ason-device AI, edge inference, on-device inference
Last reviewed2026-06-24

Example: What you trade for privacy and latency

On-device, the audio never leaves the phone and there is no network round trip. The cost is capability: you are running a few-billion-parameter quantised model against a frontier model in the cloud. Edge wins where the data must not move or the latency budget is tens of milliseconds — not where the task is hard.

Commonly confused with

Edge AI is not the same as a small model. Edge is where inference runs; a small model is what runs there. You can serve a small model in the cloud, and a well-provisioned edge device can run a surprisingly large one. The constraint is the device, not the label.

When to use it

Reach for it when:

  • Data must not leave the device for legal or contractual reasons
  • The network is unreliable or absent
  • Per-request cloud cost at your volume is prohibitive

Reach for something else when:

  • The task genuinely needs frontier capability
  • You cannot update models across a fleet you do not control
  • Device thermal and battery limits would make it unusable in practice

Referenced by

This term is used by the following ModelRefs references:

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Edge AI — AI Glossary.

Frequently asked questions

What is Edge AI?

Running AI models directly on-device (phone, IoT sensor, laptop) rather than sending data to a cloud inference endpoint.

Is Edge AI the same as on-device AI?

Yes — on-device AI, edge inference, on-device inference are common aliases for Edge AI.

What concepts are related to Edge AI?

Closely related concepts include quantization, model distillation, gguf, ollama.