A terminal tool for finding best fitted LLM models for your machine.
A terminal tool that right-sizes LLM models to your system's RAM, CPU, and GPU. Detects your hardware, scores each model across quality, speed, fit, and context dimensions, and tells you which ones will actually run well on your machine. Ships with an interactive TUI (default) and a classic CLI mode. Supports multi-GPU setups, MoE architectures, dynamic quantization selection, speed estimation, and local runtime providers (Ollama, llama.cpp, MLX, Docker Model Runner, LM Studio).
A terminal tool that right-sizes LLM models to your system's RAM, CPU, and GPU. Detects your hardware, scores each model across quality, speed, fit, and context dimensions, and tells you which ones will actually run well on your machine. Ships with an interactive TUI (default) and a classic CLI mode. Supports multi-GPU setups, MoE architectures, dynamic quantization selection, speed estimation, and local runtime providers (Ollama, llama.cpp, MLX, Docker Model Runner, LM Studio).
To install llmfit, run the following command in macOS terminal (Applications->Utilities->Terminal)
sudo port install llmfit
To see what files were installed by llmfit, run:
port contents llmfit
To later upgrade llmfit, run:
sudo port selfupdate && sudo port upgrade llmfit
Reporting an issue on MacPorts Trac
The MacPorts Project uses a system called Trac to file tickets to report bugs and enhancement requests.
Though anyone may search Trac for tickets, you must have a GitHub account in order to login to Trac to create tickets.