Imagine you need to integrate AI into your web app. Let's say you want to quickly translate text. Preferably, you'd like to use something free and open source (you don't want any surprise bills at the...

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

In this article, you will learn how sentence embeddings work and how to build a fully client-side semantic search engine using Transformers.js, with no server, no API key, and no backend infrastructure required.

HuggingFace's Transformers.js v4 rewrites its WebGPU runtime in C++, supports 200+ architectures, and delivers up to 4x faster inference in browsers and server-side JS runtimes.

HuggingFace's Transformers.js v4 rewrites its WebGPU runtime in C++, supports 200+ architectures, and delivers up to 4x faster inference in browsers and server-side JS runtimes.

The future of AI is on the edge – and increasingly, in your browser. Forget costly server infrastructure and privacy concerns. Transformers.js empowers you to run powerful Large Language Models...

𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿𝘀.𝗷𝘀 𝘃𝟰 𝗣𝗿𝗲𝘃𝗶𝗲𝘄 𝗶𝘀 𝗻𝗼𝘄 𝗔𝘃𝗮𝗶𝗹𝗮𝗯𝗹𝗲 𝗼𝗻 𝗡𝗣𝗠! https://lnkd.in/dhYy5h26 𝗪𝗵𝗮𝘁'𝘀 𝘁𝗵𝗲 𝗯𝗶𝗴𝗴𝗲𝘀𝘁 𝗰𝗵𝗮𝗻𝗴𝗲? A new #WebGPU runtime completely rewritten C++, built with the #ONNX team. The new runtime enables hardware-accelerated model inference directly in browsers and server-side JavaScript environments. It uses ONNX Runtime to execute models: this brings support for advanced architectural patterns like MoE, Mamba, and MLA to Transformers.js. 𝗪𝗵𝘆 𝗶𝘀 𝗶𝗺𝗽𝗼𝗿𝘁𝗮𝗻𝘁? The system can now handle models exceeding 8B parameters, like the demo in the post below, showing GPT-OSS 20B running entirely in-browser at decent speeds (if you have a good GPU and enough memory, ofc!). WebGPU has been around for quite sometime (https://lnkd.in/degJwwjv), but is now available in macOS Tahoe 26, iOS 26, iPadOS 26, and visionOS 26 making it a first class citizen on #Apple hardware, including #VisionPro headset. 𝗪𝗵𝗮𝘁 𝗱𝗼𝗲𝘀 𝗶𝘁 𝗺𝗲𝗮𝗻? Edge AI in the browser is here! The browser is the most universal runtime we have, it’s an obvious place to push real on-device inference. I'm looking forward to build a complete edge AI pipeline powered by Transformers.js that uses WebGPU for hardware acceleration. #Edge #AI #TransformersJS #WebAssembly #WebGPU #Apple #AppleVisionPro

Key Takeaways Transformers.js v4 now available on NPM after 11 months of development starting March 2025 WebGPU runtime delivers 4x speedup for BERT models and supports 20B parameter models at 60 tokens/sec Build times dropped from 2 seconds to 200 milliseconds with 53% smaller bundle sizes Works across Node, Bun, Deno, and all major browsers with full offline capability Hugging Face released…

The world of AI in JavaScript just got a massive upgrade. Hugging Face has officially released the preview version of Transformers.js v4 on NPM, making it easier than ever for developers to experiment with state-of-the-art AI models directly in the browser or server-side environments. After nearly a year of intense development, this new version promises a host of performance, modularity, and usability improvements that could redefine how AI is integrated into JavaScript applications.

A few days ago, Google DeepMind released a new embedding model based on the Gemma open weight model: EmbeddingGemma. With 308 million parameters, such a model is tiny enough to be able to run on edge ...

🎉 Am **Mittwoch, 27. August 2025** gehts wieder los mit Bärner JS! Es erwarten euch spannende Talks von [Nico Martin](https://nico.dev) sowie [Daniel Reiter & Benjamin Cir

How I used Hugging Face embeddings to create smart “Related Posts” for my Astro blog—no backend, no database, just TypeScript.