Wend.
ProductPricing
Sign inGet access
Glossary/On-device AI

On-device AI

On-device AI is machine learning that runs on the user's own phone or computer rather than on a server, so the data being processed stays on the machine.

On-device AI means the model runs where the data already is: the phone or computer in front of you, not a data center. It became practical for consumer software between 2024 and 2026, when every major platform shipped a system model applications can call. Apple exposes its Foundation Models through Apple Intelligence, Android ships Gemini Nano, and Windows runs models on the NPUs in Copilot+ machines. An application no longer has to bundle a model; it asks the operating system for one.

The trade is capability for locality. A system model is small, so it is good at bounded jobs: pulling structured facts out of text, reading a card or a screenshot, classifying, summarizing short inputs. It is not a frontier reasoning engine, and treating it as one produces bad answers with local latency. Mature designs route instead: the job runs on the device when a small model does it well, and goes to a large hosted model when it does not. The routing decision, not either engine alone, is the architecture.

What running locally buys is concrete. Latency drops to what the silicon can do, marginal cost drops to zero, the feature works offline, and the raw input never has to be transmitted to be understood. That last property is the interesting one for personal data, because a hybrid system can keep the raw material local and move only the structured result, which changes what the product has to be trusted with.

Why it matters

The label is doing heavy marketing work right now, and it often covers only part of a pipeline. The useful evaluation questions are which jobs actually run on the device, what leaves it, and what happens when the local model is unavailable. A product with a clear answer to all three has an architecture; one without has a slogan.

How Wend relates

Wend routes each job to the engine that runs it best. On Apple silicon with Apple Intelligence turned on, it extracts facts, reads business cards, and builds briefings on the Mac itself, measured live at 2.4 seconds for a natural-language extraction, at no cost. Big jobs route to the cloud; the sensitive raw never does.

Get access

Related terms

Agent-nativeRelationship memoryModel Context Protocol (MCP)Provenance
PreviousNetwork mappingNextPersonal CRM
All terms

Wend.

Wend.

Wend knows everyone you know, notices who you talk to, and plugs your whole network into the AI you already use. Every fact has a source, and you approved it.

Product

  • Get access
  • Wend for Mac
  • Planner
  • Manifesto
  • Pricing
  • Wend for Chrome
  • Open source (wend-core)
  • Sign in

Compare

  • Best personal CRMs 2026
  • Wend vs Dex
  • Wend vs Mesh (Clay)
  • Dex alternatives
  • Mesh (formerly Clay) alternatives
  • Monica HQ alternatives
  • Assistant memory alternatives
  • All alternatives
  • All head-to-heads

Use cases

  • For founders
  • For investors
  • For chiefs of staff
  • For job-seekers
  • All audiences

Free tools

  • Warm-intro response rate
  • Who do I know at…
  • Intro request template
  • Follow-up cadence
  • All free tools

Resources

  • Blog
  • Glossary
  • Security & privacy
  • About

Company

  • Your account
  • Contact
  • Privacy
  • Terms
  • Subprocessors
  • DPA
Encrypted at rest·Never sold·Never used to train AI·Open core (AGPLv3)·GDPR transfers via SCCs·Sitemap

© 2026 Wend Labs Inc. · trywend.io

Built by Ansh Vasani and Ava Yu.

Ask AI about Wend

PerplexityChatGPTGoogle