r1-web

WebGPU inference for DeepSeek-R1

AuthorSurya Dantuluri
Published
Views600K from New York City, San Francisco, Meerut

WebGPU inference for DeepSeek-R1 — runs entirely in your browser, no downloads, no server. Open source, made in America, run on American servers.

Later extended to run Qwen3 0.6B with thinking locally via WebGPU, including experimental mobile support. Uses transformers.js with ONNX conversion under the hood.