It has A19 Pro. A19 Pro has matmul acceleration in its GPU, the equivalent of Nvidia's Tensor cores. This would make future Macs extremely viable for local LLMs. Currently, Macs have high memory bandwidth and high VRAM capacity but low prompt processing speeds. Give it a large context and it'll take forever before the first token is generated. If the M5 generation gets this GPU upgrade, which I don't see why not, the…
Luckily they added the blood pressure check for when you get too excited about the color orange.