WebLLM and Javascript API

WebLLM is a MLC chat web runtime (WebLLM) that allows you to build chat applications directly in the browser.

Try out the Prebuilt Webpage

To get started, you can try out WebLLM prebuilt webpage.

A WebGPU-compatible browser and a local GPU are needed to run WebLLM. You can download the latest Google Chrome and use WebGPU Report to verify the functionality of WebGPU on your browser.

Use WebLLM NPM Package

WebLLM is available as a npm package. Below is a simple example to use WebLLM API in your own TypeScript program. You can follow the instructions in get-started to run the example.

import * as webllm from "@mlc-ai/web-llm";

function setLabel(id: string, text: string) {
  const label = document.getElementById(id);
  if (label == null) {
    throw Error("Cannot find label " + id);
  label.innerText = text;

async function main() {
  const chat = new webllm.ChatModule();

  chat.setInitProgressCallback((report: webllm.InitProgressReport) => {
    setLabel("init-label", report.text);

  await chat.reload("vicuna-v1-7b-q4f32_0");

  const generateProgressCallback = (_step: number, message: string) => {
    setLabel("generate-label", message);

  const prompt0 = "What is the capital of Canada?";
  setLabel("prompt-label", prompt0);
  const reply0 = await chat.generate(prompt0, generateProgressCallback);

  const prompt1 = "Can you write a poem about it?";
  setLabel("prompt-label", prompt1);
  const reply1 = await chat.generate(prompt1, generateProgressCallback);

  console.log(await chat.runtimeStatsText());


Build a Chat App

You can find a complete chat app example in simple-chat.