Meet LiteRT.js: Google’s edge AI runtime for the web. Run ML models directly in the browser with high-performance WebGPU, WebNN, and WebAssembly.

KI-Modelle direkt im Browser auszuführen ist endlich schnell genug, um real zu sein. Ein praktischer Leitfaden 2026 für On-Device-Inferenz mit WebGPU und Googles neuem LiteRT.js — was sich geändert hat, wie es funktioniert und wann man es einsetzt.

Running AI models directly in the browser is finally fast enough to be real. A practical 2026 guide to on-device inference with WebGPU and Google's new LiteRT.js runtime — what changed, how it works, and when to reach for it.

Introduction: A New Era of Browser-Based Artificial Intelligence Artificial intelligence is rapidly moving away from the traditional cloud-only model toward a future where powerful AI systems can run directly on personal devices. The launch of LiteRT.js represents a major step in this transformation by bringing advanced on-device machine learning capabilities directly into modern web browsers. For years, developers have relied on browser-based AI frameworks to deliver intelligent experiences, but many solutions faced performance limitations because they depended heavily on JavaScript execution.

Google released LiteRT.js, a JavaScript binding of LiteRT. LiteRT is Google’s on-device inference library, previously called TensorFlow Lite. LiteRT.js runs .tflite models directly inside the browser. Because inference stays local, Google cites enhanced user privacy, zero server costs, and ultra-low latency. What is LiteRT.js? It is not a new model format. Rather, Google compiled its existing native runtime to WebAssembly and exposed it to JavaScript. Earlier web AI solutions, including TensorFlow.js, relied on JavaScript-based kernels. Google describes those as less performant. LiteRT.js instead ships the native cross-platform runtime with its optimizations intact. Consequently, web apps inherit work done elsewhere. Performance upgrades, quantization improvements, and hardware optimizations built for Android, iOS, and desktop arrive on the web too. How It Works: One Runtime, Three Backends Under that runtime, LiteRT.js targets three backends: CPU uses XNNPACK, Google’s optimized CPU library, with multi-thread support and a relaxed SIMD build. GPU uses ML Drift, Google’s on-device GPU solution, running through WebGPU. NPU uses the WebNN API, currently experimental in Chrome and Edge. Two related rules govern dispatch. First, LiteRT.js does not support partial delegation. A graph cannot split across CPU and GPU. Second, delegation is all-or-nothing per model. If a model cannot be fully...

Meet LiteRT.js: Google’s edge AI runtime for the web. Run ML models directly in the browser with high-performance WebGPU, WebNN, and WebAssembly.

Eyal Estrin unread, 6:39 AM (25 minutes ago)    to https://developers.googleblog.com/litertjs-googles-high-performance-web-ai-inference/ https://www.neowin.net/news/google-launches-litertjs-to-make-ai-and-ml-workloads-faster-in-the-browser/ Eyal Estrin Author | Cloud Architect | AWS • Azure • GCP Insights Social: @eyalestrin Connect: https://linktr.ee/eyalestrin Blog: https://security-24-7.com

Google has just released a new library for developers that promises to speed up local AI and ML workloads.

Meet LiteRT.js: Google’s edge AI runtime for the web. Run ML models directly in the browser with high-performance WebGPU, WebNN, and WebAssembly.

Meet LiteRT.js: Google’s edge AI runtime for the web. Run ML models directly in the browser with high-performance WebGPU, WebNN, and WebAssembly.