Transformers.js v4 rewrites its WebGPU runtime in C++ and compiles to WASM, delivering ten‑fold faster build times, 10% smaller bundles, and up to four‑fold speedups for BERT‑style models, while supporting over 20 new architectures such as Qwen3.5 and enabling offline, privacy‑preserving AI inference directly in the browser.
Chrome Canary’s experimental Gemini Nano feature enables local execution of a large language model in the browser, offering easy deployment, hardware acceleration, offline use, and a Prompt API with createTextSession and streaming calls, plus step‑by‑step instructions and a demo for in‑page translation.
This article introduces how to use the JavaScript library transformers.js directly in the browser, leveraging Google’s built‑in window.ai models, outlines supported AI tasks, demonstrates a live demo, and provides the core implementation code for model loading, worker communication, and text generation.
Paddle.js is Baidu’s lightweight JavaScript inference engine that transforms Paddle models into web‑compatible formats, enabling fast, privacy‑preserving AI features such as face detection, gesture recognition and content filtering directly in browsers via WebGL/WebAssembly, with only 201 KB code and broad compatibility.
