🧠 LLM Inference with Multi-Engine Search

⚙️ Core Settings
🤖 Model

Select the language model to use

Search across Google, DuckDuckGo, and Bing (no API required)

⏱️ Estimated GPU Time: 65.1 seconds

📊 Model Size: 4.0B parameters 🔍 Web Search: Disabled
64 16384
0.1 2
1 100
0.1 1
1 2
💡 Example Prompts

💡 Tips:

  • Use Advanced Parameters to fine-tune creativity and response length
  • Enable Web Search for real-time information (uses multiple search engines)
  • SafeSearch is OFF for comprehensive results
  • Try different models for various tasks (reasoning, coding, general chat)
  • Click the Copy button on responses to save them to your clipboard