LOCAL

C++ inference engine for LLMs. GGUF format, quantization, CPU and Metal/CUDA support. The foundation most local tools build on.

Dictation on Mac that actually works. Uses Whisper locally, with optional LLM post-processing for formatting and punctuation.

Apple's array framework for machine learning on Apple Silicon. Native Metal support, unified memory, first-class LLM inference.

Install Ollama and LM Studio, pull your first model, and run AI locally for coding, chat, and automation - with zero cloud dependency.