A field guide to AI positions

On-device AI / edge AI

Dated sources are over 18 months old; other dates are unknown.

Publication dates and source age

Sources counted: 2

Newest dated source: 2022-02-23

Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

Some publication dates are unknown; the newest dated source may not be the newest source overall.

Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

Open in the glossary Reading notes · Structured record

In plain language

Running a model on a device such as a phone or laptop. Where a calculation runs does not by itself establish the privacy of the whole app. [1] [2]

Reference this explanation or suggest a correction

Link to this explanation · Suggest a correction · How corrections work

Limits & distinctions

On-device inference is different from training on the device. To assess privacy, check the whole application’s data flows, including any other services it uses. [1] [2]

Reference this explanation or suggest a correction

Link to this explanation · Suggest a correction · How corrections work

A fuller explanation

On-device AI runs model calculations locally. A model can be obtained or trained elsewhere, adapted for the target device and then run there. Edge AI is also used for processing near the source of data. [1]

Reference this explanation or suggest a correction

Link to this explanation · Suggest a correction · How corrections work

How it relates to the map

Map context: this describes where computation happens. We do not treat local processing as a movement or a position on frontier pacing. [1]

Reference this explanation or suggest a correction

Link to this explanation · Suggest a correction · How corrections work

Share this page

https://theaiatlas.org/ideas/on-device-ai/

Download a share image · Vector image

Image previews are summaries. Keep the page link so readers can check the evidence.

Sources and what we read

  1. 1. LiteRT: High-Performance On-Device Machine Learning Framework

    Publication dates and source age

    Sources counted: 1

    Publication dates are unavailable.

    Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

    Some publication dates are unknown; the newest dated source may not be the newest source overall.

    Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

    Read the platform overview and deployment workflow for running models on devices. The entry describes the location of computation, without adopting blanket vendor claims about privacy, speed or capability.

  2. 2. System Cards, a new resource for understanding how AI systems work

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2022-02-23

    Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

    Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

    Read the system-card proposal, its distinction from model cards and its limitations section. Meta describes its own approach; publication of a card is not an independent audit of the system.

Edition and machine-readable evidence

Content version 0.20.0. Evidence cutoff 2026-09-15; this does not mean every source was read on that day.

Pinned complete dataset · Complete evidence page · Agent consumption guide