An LLM inference server designed for Apple Silicon that enhances performance through continuous batching and SSD caching, easily managed from the macOS menu bar. It streamlines the process of running large language models, making it more efficient for users on Mac systems.
Categories & Topics
Repository Stats
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?v=4)
Related Tools
agent-safehouse
Sandbox your LLM coding agents on macOS so they can only touch the files they need. Useful for ai-agents and claude-code use cases.
AgentCPM
AgentCPM provides a comprehensive framework for training and assessing different language model agents. It simplifies the process of developing and evaluating these agents, making it easier for users to create effective AI-driven solutions.
AppPorts
📦 A macOS utility to seamlessly migrate applications to external storage and reclaim local disk space.【一款 macOS 工具，无缝迁移应用到外部存储并自动建立链接，释放宝贵的本地空间】
BetterCmdTab
Master your Mac’s ⌘Tab
brew-browser
Homebrew is the standard package manager on macOS. brew-browser gives it a real native GUI.
claude-desktop-zh-cn
Claude Desktop Chinese Patch (macOS & Windows)