llama.cpp

Local inference engine for GGUF models.

llama.cpp runs quantised models on your own machine. It is a lower-level runner than Ollama or LM Studio. Setup friction is part of the point.

This description identifies the product. It is not a test result, a rank, or a FitScore.

Scores by job

Local / open models
Easiest way to run a good model on my own machine?
—
Not yet testedUnranked
No published FitScore. The job page lists this tool as not yet tested.