WebLLM
webllm.mlc.ai
In-browser LLM inference powered by WebGPU — runs full language models entirely inside Chrome or Edge with no server, no API key, and no data leaving your device.
Why it is useful
A technically remarkable demo that is also genuinely useful: once the model downloads to your browser cache, it works completely offline with no API costs. Privacy is absolute since computation happens in your GPU through WebGPU. Performance on recent hardware is surprisingly close to server-side inference for 3–7B models. Worth knowing about for privacy-sensitive applications or offline use cases.
More in Hidden Websites
Other hidden websites you might not have heard of.
- Damn InterestingLong-form, meticulously researched articles on obscure true stories — history, science, and disasters most people have never heard of.
- Dan QThe personal blog of Dan Q, a long-running site that covers technology, the web, geocaching, travel and everyday life, with posts going back many years.
- dCodeA large set of tools for solving ciphers, codes, puzzles, number problems and games, with explanations of how each method works.
- KiwixSoftware and downloads that let you read Wikipedia and other large reference collections offline, on a phone, a computer or a small device.
- Library of Short StoriesFree collection of classic short stories from various authors in a simple reading format.
- WikisourceA free library of source texts, including books, documents and historical papers, transcribed and proofread by volunteers.