llama.cpp
The C++ inference engine most local AI tools are built on, including Ollama and LM Studio. It runs on CPU, CUDA, Metal and Vulkan, which is why the GGUF files it reads work on almost any machine. The quant recipes with names like Q4_K_M and IQ3_XXS are its.
Almost nobody runs it directly. It matters because it sets the vocabulary: when a model listing offers you six files with letters after the bit depth, those letters come from llama.cpp, and so does the reason the same file works on a Mac, a Windows box and a Raspberry Pi.