WebLLM · Mobile + Desktop · WebGPU

Local AI Chat

Run open-source LLMs entirely in your browser. No server, no API keys — powered by WebLLM.

Qwen3 · Llama · Gemma Streaming Markdown
▾
Powered by WebLLM + MLC-AI
Initializing engine…
Model is cached after first download.
W
WebLLM Chat
Ready
Temp0.70
Top-P0.95
Tokens
Rep1.10

Start a conversation

Type a message below.
Everything runs locally in your browser.

100% local — no data leaves your device.