WebLLM.io Playground

WebGPU Checking...

VRAM —

Grade —

Model —

Status Idle

Battery —

Local Tokens 0

Cloud Tokens 0

Run Mode

Local Config

Model ID

Browse on GitHub →

WebWorker

OPFS Cache

Cloud Config

Base URL

API Key

Model Name

Timeout (ms)

Retries

WebLLM.io Playground

Run large language models directly in your browser.