Services
On-device AI in your app
The AI models on your users’ phones are now good enough for real product features. We integrate them: private by design, working offline, with no per-token cost.
In plain English
On-device AI means the model runs on the phone itself, not on a server. Your app can summarize, draft, classify, and extract without sending user data anywhere. Apple ships this as Apple Intelligence with the Foundation Models framework. Android ships it as Gemini Nano.
Why on-device
- Private by design. User data stays on the device for on-device features. No AI provider in the loop, a far simpler GDPR story.
- No cloud token bill. Cloud LLM features cost money on every request. The on-device path does not; only your cloud fallback needs a budget.
- Fast and offline. No network round trip. Features keep working on the train, in the basement, and in airplane mode.
What we integrate
- Apple Intelligence (iOS) via the Foundation Models framework: guided generation and tool calling today, plus image understanding and Private Cloud Compute access announced at WWDC 2026 (in beta, shipping with iOS 27)
- Gemini Nano (Android) via the ML Kit GenAI APIs: summarization, proofreading, rewriting, and image description on recent flagship devices
- Hybrid architectures, also in Flutter: on-device first, a cloud model as fallback, one feature layer on top
- App Intents and App Actions where the feature should also be reachable through Siri or Gemini
The honest boundaries
On-device models are small. They will not replace a frontier cloud model for deep reasoning, long documents, or broad knowledge. Device coverage varies, so older phones need a fallback path. The right architecture decides per feature: on-device where it fits, cloud where it earns its cost, and a graceful degradation everywhere else. That decision is the core of this service.
How we work
We start with your product, not the framework. Which features benefit from AI at all? Which of those fit an on-device model? We map that, prototype the risky parts, then build the feature layer with fallbacks, evals, and a quality bar your team can maintain. For agent features that act on user data, we bring the same consent-and-permissions thinking as our AI agent work.
Frequently asked questions
What does on-device AI cost per request?
There is no cloud token bill on the on-device path. Apple Foundation Models and Gemini Nano run on the user’s device, so the platform charges nothing per request. Plan for the boundaries anyway: device coverage varies, platforms can impose quotas, and the cloud fallback still needs a budget.
Which devices support on-device AI?
Apple Intelligence needs an iPhone 15 Pro or newer, plus recent iPads and Macs. On Android, Gemini Nano runs on recent flagship devices. We design every feature with a fallback path for devices that do not qualify.
Is on-device AI enough, or do we still need a cloud model?
It depends on the feature. On-device models are small. They handle summaries, drafting, classification, extraction, and guided flows well. Heavier reasoning still belongs in a cloud model. Most products end up hybrid: on-device first, cloud where needed, with clear user consent.
Why is on-device AI good for privacy and GDPR?
For the on-device path, user data never leaves the phone. No third-party AI provider processes it, which simplifies your privacy story and your data-processing agreements. We are engineers, not lawyers, but this architecture gives your legal team much less to worry about.