NeuralPocket: Private On-Device AI with Gemma 4 — Android & Web

Code

Both projects are fully open source:

• 🤖 Android (Kotlin + LiteRT-LM) →
  


• 🌐 Web (React 19 + TypeScript + WebGPU) →
  
  
  
  
  
  
  
  

  
  
  
  Web: WebGPU Right in the Browser
  

  
  
  

  Stack: React 19 + TypeScript + Vite + Tailwind CSS v4 + MediaPipe Tasks GenAI

  
  
  

  All inference runs inside a Web Worker — generation never blocks the UI, keeping the interface responsive during streaming. Models are cached in OPFS (Origin Private File System): first launch downloads ~2.6 GB, every subsequent launch starts instantly without a network connection.

  
  
  

  Three model presets are supported: Gemma 4 E2B, Gemma 4 E4B, and Gemma 3 Multimodal. You can also provide a custom model URL.

  
  
  

  The web app is built as a PWA (Progressive Web App) — you can install it on your computer as a standalone app with one click from the browser, just like YouTube or other web services. Once installed, it appears in your app menu and opens in its own window without an address bar.

  
  
  
  
  
  
  

  Honest caveat about offline: after the first launch the app works without a network. But it's not fully autonomous out of the box: the MediaPipe runtime loads from jsDelivr, and fonts load from Google Fonts. For full offline you'd need to self-host those dependencies.

  
  
  

  Honest caveat about multimodal in the web: at the time of development I couldn't find web-optimized multimodal models for Gemma 4 — available versions only support text. However, I found a fully multimodal model from the previous generation — gemma-3n-E2B-it-int4-Web.litertlm — which supports displaying text, images and audio directly in the browser. That became the third preset in the web version.

  
  
  

  
  

  A note on how fast things move. While building NeuralPocket, Google released Gemini 3.5 Flash — and first impressions suggest it's a notable step up from 3.1. It handles complex multi-step tasks confidently: for example, it wrote a full test suite for the web version of NeuralPocket on the first try, something that used to take several iterations. It's remarkable how fast this space evolves — the world changes while you're still writing the article.

  
  
  

  At this pace, in a year you might just need to download the latest Gemma and ask it to build the whole app itself. Probably. Maybe. 😄

  
  

  
  
  
  
  
  

  
  
  
  Privacy as Architecture, Not Marketing
  

  
  
  

  NeuralPocket sends nothing anywhere — not messages, not photos, not chat history, not analytics. This isn't a setting you toggle. It's a consequence of the architecture: there's no server that could receive anything. Works in airplane mode. No account, no subscription.

  
  
  
  
  
  

  
  
  
  Summary: Android vs Web
  

  
  
  

  Two apps, one idea — but different trade-offs:

  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  

  	🤖 Android	🌐 Web
  Installation	APK (~36 MB)	None — just open in browser
  Install as app	✅ native	✅ PWA
  Model	Gemma 4 E2B / E4B	Gemma 4 E2B / E4B
  Text chat	✅	✅
  Photo input	✅	⚠️ Gemma 3n only
  Audio input	✅	⚠️ Gemma 3n only
  Offline	✅ after downloading	⚠️ after first launch
  	models	and downloading models
  Performance	~15–30 tok/s (GPU)	depends on browser WebGPU
  Requirements	Android 8+, arm64	Chrome / Edge with WebGPU
  Multiple chats	✅	✅
  Custom model	❌	✅ by URL

  
  
  

  Need maximum multimodality and full offline? Go Android. Want to try it right now without installing anything? Go Web.

  
  
  

  🤖

  
  
  
  
  
  

  📦 Models: on HuggingFace

  
  
  

  Built with ❤️ on Gemma 4 + Google AI Edge LiteRT-LM

  Vollständiger Original-Bericht

  Ausführliche Details, Code-Beispiele & Hersteller-Stellungnahme auf dev.to.

  ↗ Original-Artikel auf dev.to lesen