llama-3.1-8B-q4 on: - M1 Air 16G → 19 tok/s - M1 Pro 16G → 27 tok/s - M2 Pro 32G → 38 tok/s - M3 Pro 36G → 42 tok/s - M3 Max 64G → 71 tok/s - M4 Max 128G → 84 tok/s (!) Memory bandwidth correlates almost linearly with t…