Apple Silicon (M3 Ultra / M4)

Apple's M-series chips are the bandwidth leaders among unified-memory machines. The M3 Ultra runs at 819 GB/s — roughly 3× any Strix Halo or GB10 box — and at launch scaled to 512GB, enough to hold DeepSeek R1 671B at 4-bit in memory (~17–18 tok/s, under 200W). The M4 family spans a wide range: 120 GB/s on the base Mac mini (a 24GB, ~7–14B-class entry point), 273 GB/s on the M4 Pro, and 410–546 GB/s with up to 128GB on the M4 Max. The catch is software — no CUDA, so you run MLX, llama.cpp, or Ollama.

Apple wins on tokens/sec per dollar of bandwidth but loses on CUDA-only tooling and (as of 2026) capacity — the 256/512GB Ultra configs were pulled in the DRAM shortage. Pick the tier by model size: base M4 for small models, M4 Max or M3 Ultra for frontier ones.