local-ai Server

⚙️ Configuration

Select a model and configure parameters

Select Model:

▶ Model Parameters

Temperature 0.7 Lower = more deterministic, Higher = more creative

Top P 1.0 Nucleus sampling threshold

Max Tokens 4096 Maximum response length

Seed Random For reproducible outputs (optional)

System Prompt

Tool Mode: Off (Enable to test function calling)

Available Tools

Welcome to local-ai! Select a model and type a message to test it.

▶ Show Debug Info

Debug Info:

Models available: {{ models|length }}