FICHA · AUR

lemonade-server

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

  • llm-server
  • Server
  • Dev
  • HARDWARE
  • Launchable
  • Runs in terminal
  • Background service
official+codex · reviewed · Jun 1, 2026 description in en

Description

Local language models can be served over a server process with GPU or NPU acceleration. It is useful for developers who want local AI inference exposed to tools or applications on the same machine or trusted network.

LLM servers can process private prompts and may expose an API. Restrict listening interfaces, review model sources, and avoid sending sensitive data to untrusted clients.

How to run

lemonade-server

Commands: lemonade-server

Permissions

Permissions not analysed for this source yet.