Right-sizes LLM models to your system's RAM, CPU, and GPU
Summary
The llmfit README describes a terminal tool that right-sizes LLM models to a system's RAM, CPU, and GPU. It detects hardware, scores models across quality, speed, fit, and context, and selects the best quantization and run mode, while supporting multiple local runtimes and MoE architectures; it also maintains a HuggingFace-based model database with automation for updates.