Apple's MLX Runs Local LLMs 3x Faster Than llama.cpp — Until Your Context Hits 40KOllama just got 93% faster on every Apple Silicon Mac, and it did it without touching the model, the quantization, or the hardware. Version…Apple's MLX Runs Local LLMs 3x Faster Than llama.cpp — Until Your Context Hits 40KOllama just got 93% faster on every Apple Silicon Mac, and it did it without touching the model, the quantization, or the hardware. Version…Chew Loong Nian - AI ENGINEER·May 15