Run language models in your browser. No servers. No data collection.
Bring large language models to the client side with WebLLM's privacy-first inference engine. No API calls. No rate limits. Your data stays yours.
Inference happens in your browser. Zero server calls. Complete user privacy.
WebGPU acceleration. Optimized model weights. Instant responses in milliseconds.
Deploy Llama, Mistral, Gemma, and Phi. Bring your own quantized GGUF weights.
Clean JavaScript API. Drop into any web app. Comprehensive documentation. MIT licensed.
No external API dependency. Audit-friendly architecture. Zero data transmission.
Pre-quantized models. Automatic browser detection. Production-ready in minutes.
Install WebLLM and run your first inference in under 5 minutes.
npm install @mlc-ai/web-llm
import * as webllm from "@mlc-ai/web-llm";
const engine = new webllm.MLCEngine({
model: "Llama-2-7b-q4f32_1"
});
const response = await engine.chat.completions.create({
messages: [{role: "user", content: "Hello"}]
});Register interest
This is not a purchase and there is no card field. It puts your address, this product, and whatever you write below in front of a person, and you get a written answer about what finishing it, or handing it over for you to run yourself, would actually take.