M3 Max

DeepSeek V4 Flash, a 284-billion-parameter Mixture-of-Experts model, now runs locally on a 128GB MacBook Pro via antirez's experimental llama.cpp fork, achieving ~21 tokens/sec generation on the Metal…

A developer reports that running local LLMs for code completion is now faster and more private than using cloud APIs. Using Ollama with a 7B model on an M3 Max MacBook Pro, they achieved sub-second co…