# LiteRT.js: Run ML Models in the Browser Without a Server

> Google wraps its native LiteRT C++ runtime in WebAssembly, delivering 3x faster CPU inference than TensorFlow.js and 5-60x GPU speedups via WebGPU. Semantic search, object detection, and image upscaling run entirely client-side - no API, no server cost, no data leaving the browser.

Canonical URL: https://kravhal.kcsatish.com/insights/week-39
Edition: Article 18 · July 2026
Tags: On-Device AI, WebAssembly, Inference
Reading time: 8 min read

---

This is a mirror of an article first published in the AI & Automation Chronicle.

Full text with the original formatting: https://chronicle.kcsatish.com/posts/week-39
Markdown of the original: https://chronicle.kcsatish.com/posts/week-39.md
Structured JSON of the original: https://chronicle.kcsatish.com/api/v1/posts/week-39.json

Cite the Chronicle as the publication of record for the research claims in this article.