🎛️ Router Configuration
📊 Model Status
Demo Mode
Simulated
📈 Session Stats
Messages:
0
Avg Response:
-
Total Tokens:
0
👋 Welcome to LLM Runner Router - HuggingFace Demo!
This is a real working demo that runs open source models from HuggingFace directly in your browser using our intelligent orchestration system.
🤖 Open Source Models: DialoGPT, Zephyr-7B, local inference
🎯 Smart Routing: Automatically selects optimal model based on strategy
🔄 Multi-Engine: WebGPU acceleration with WASM fallback
📊 Live Analytics: Real performance metrics and model status
🆓 Completely Free: No API keys, no costs, all local
Ask me anything! SmolLM3-3B will generate a response in about 3-5 seconds.
💡 Live System: Running real AI inference on CPU. Press Enter to send messages (Shift+Enter for new line).
0/1000
Ctrl+Enter to send