Built with Metal

llama.cpp

llama.cppAIOpen

Inference engine that runs LLMs on almost any hardware

llama.cpp is the layer most local model tooling is built on. It is a C and C++ inference engine with no Python runtime, aggressive quantisation support, and hand-tuned kernels for a remarkably wide range of hardware.

whisper.cpp

whisper.cppAIOpen

Speech recognition that runs anywhere, with no runtime

whisper.cpp is a C and C++ port of the Whisper speech recognition model with no Python dependency, quantised weights, and hardware acceleration across Apple Silicon, CUDA, and plain CPU.