find which LLMs your hardware can actually run
llmfit right-sizes Large Language Models to your system's RAM, CPU and GPU.
It detects your hardware, scores hundreds of models across quality, speed,
fit and context dimensions, and tells you which ones will actually run well
on your machine. It ships with an interactive TUI (default), a classic CLI,
and a web dashboard / REST API (llmfit serve), and talks to local runtime
providers such as Ollama, LM Studio, vLLM and Docker Model Runner.
For a convenient alias:
sudo snap alias llmfit-bp.llmfit llmfit
To let llmfit detect your GPUs (PCI devices and VRAM via sysfs):
sudo snap connect llmfit-bp:hardware-observe