Search the archive.
Find published work and reporting by title, description, article text or tag.
Refine results
Also searching for Browser AI, because “in-browser-inference” is another name for it.
6 results for “in-browser-inference”.
AI Grid: Run LLMs in Your Browser, Share GPU Compute with the World
AI Grid connects browser tabs into a peer-to-peer compute mesh. Run LLMs locally with WebGPU, share spare GPU cycles, or borrow from others. No installs, no cloud. Just a URL and your graphics card.
Ranked results
- Showcase
PipeMagic: A WebGPU Node Editor for Image Pipelines
A node editor for image pipelines that runs entirely in the browser. Wire up background removal, depth estimation, JFA outlines, and 2x upscale, watch WebGPU do the work, then export the graph as JSON and drop the same logic into your app in roughly 180 lines.
- Showcase
Semantic Globe: A WebGPU Earth That Understands Plain English
Type a vibe like "somewhere cold and lonely" and watch a 3D Earth pin the answer. The text embeddings and the planet shaders share one GPU in one browser tab, no server in the loop. Joshua Lochner's quiet flex of what WebGPU can do when nobody is looking.
- Showcase
LFM2-MoE: An 8.3B Parameter Language Model Running Entirely in Your Browser via WebGPU
Liquid AI's LFM2-MoE loads 8.3B parameters (1.5B active) and generates text client-side through WebGPU. No server, no API key. A hybrid convolution-attention architecture running Mixture-of-Experts inference in a browser tab, powered by Transformers.js.
- News
Google Brings LiteRT Inference to the Browser With WebGPU
Google has brought its LiteRT on-device inference stack to the browser, with XNNPACK on CPU, ML Drift over WebGPU, and experimental WebNN support for NPUs.
- Showcase
WebGPU Cluster Turns Browsers Into AI Inference Nodes
Alexsandro Souza’s WebGPU Cluster turns browser tabs into shared AI inference nodes, with WebGPU hosts running RF-DETR or SmolVLM behind a simple HTTP API.
