Phi-3 WebGPU is a web app that allows users to run the Phi‑3 language model directly in their browser using WebGPU, enabling fast, local AI text generation. It's aimed at AI researchers and developers interested in local LLM experimentation.
Phi-3 WebGPU sits in PulseGate's Foundation models & chat category. It focuses on running large language models directly in the browser for private, fast AI text generation without cloud dependency. Phi-3 WebGPU is a B2B product aimed at AI researchers. It is available for free. Phi-3 WebGPU is available on the web.
It is developed by Xenova, and it first shipped in 2024. Among its 4 catalogued features are local inference, webGPU support, and prompt input.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do