핵심은 와트당 성능이었어

#!/usr/bin/env python3
"""Joules per token, bounded. Power figures are vendor maxima (Apple's tested
maximum for the exact office configuration; NVIDIA board power). Decode rates
are measured (office) or ceiling arithmetic (the card) — the labels say which."""

rows = [
    # machine,                        watts, tok/s,  power label,           rate label
    ("office M3 Ultra, Qwen3.5-27B 4-bit", 270, 32.6, "vendor max (Apple)",   "measured 2026-09-15"),
    ("office M3 Ultra, Qwen3.5-9B 4-bit",  270, 95.1, "vendor max (Apple)",   "measured 2026-09-15"),
    ("RTX 5090, 14.4 GB model (fits)",     575, 1792 / 14.4, "vendor board power", "ceiling = 1792 GB/s ÷ 14.4 GB (physics, not measured)"),
]

print(f"{'machine / model':38} {'W':>4} {'tok/s':>6} {'J/token (upper bound)':>22}")
for name, w, tps, plabel, rlabel in rows:
    print(f"{name:38} {w:4d} {tps:6.1f} {w / tps:22.2f}   [{plabel}; {rlabel}]")

print("\nA bound is not a measurement. Replace the watts with a powermetrics sample:")
print("  sudo powermetrics --samplers cpu_power,gpu_power,ane_power -i 1000 -n 30")
print("while a model decodes; add CPU + GPU power, divide by tokens per second.")

# terminal 1: decode something for ~30 s in your MLX env
python -m mlx_lm generate --model mlx-community/Qwen3.5-9B-4bit \
  --prompt "Explain unified memory in 400 words." --max-tokens 300

# terminal 2: sample power once a second for 30 s
sudo powermetrics --samplers cpu_power,gpu_power,ane_power -i 1000 -n 30 \
  | grep -E "CPU Power|GPU Power|ANE Power"
# CPU Power: 1234 mW
# GPU Power: 45678 mW      <- the number that matters for decode
# ANE Power: 0 mW          <- the Neural Engine is idle; MLX runs on the GPU

# joules per token = (CPU mW + GPU mW) / 1000 / tokens-per-second