Llmfit is a terminal tool that helps users find the best large language models (LLMs) for their hardware. It detects system specifications, scores models based on quality, speed, fit, and context, and recommends the most suitable models for the user’s system. llmfit supports various hardware configurations, including multi-GPU setups and Mixture-of-Experts architectures, and provides both interactive and classic CLI modes.

Llmfit is a command-line interface (CLI) tool for managing and running large language models (LLMs). It integrates with Ollama to detect installed models, download new ones, and provides a terminal user interface (TUI) for model selection and management. llmfit also ships as an OpenClaw skill, enabling hardware-aware model recommendations and automatic configuration of Ollama, vLLM, and LM Studio providers.

Llm-checker is a Node.js CLI tool that benchmarks models directly using Ollama, providing real-world performance data. It doesn’t support Mixture-of-Experts architectures.