FICHA · AUR

lemonade-desktop

Lemonade: Local LLM Serving with GPU and NPU acceleration (GUI)

  • llm-desktop-app
  • GUI
  • Dev
  • HARDWARE
  • Launchable
official+codex · reviewed · Jun 1, 2026 description in en

Description

Local language models can be served and managed from a graphical app with GPU or NPU acceleration. It is useful for users who want local AI inference without relying entirely on remote model providers.

Local LLM tools can process private prompts, files, and generated output. Review model sources, hardware use, and any network sharing before loading sensitive data.

How to run

lemonade

Commands: lemonade

Permissions

Permissions not analysed for this source yet.