Lemonade System Requirements (CPU, RAM, Disk)

Lemonade helps you discover and run local AI apps by serving optimized LLMs directly from your own GPU or NPU. It is a lightweight, OpenAI-compatible local server that keeps your data private while delivering fast inference on consumer hardware. Built on ONNX Runtime with Vulkan, ROCm, and NPU acceleration, it supports models like Llama, Mistral, and Qwen without cloud dependencies.