디코드 상한: 대역폭 ÷ 토큰당 바이트

#!/usr/bin/env python3
"""Bytes a token must read during decode, from the checkpoint's own headers.
Rules: skip the vision tower; skip the embedding table unless tied to the
head; count routed experts at k/E; count everything else once."""
import json, struct, sys
from pathlib import Path
from huggingface_hub import snapshot_download

repo = sys.argv[1] if len(sys.argv) > 1 else "mlx-community/Qwen3.5-9B-4bit"
path = Path(snapshot_download(repo, local_files_only=True))
cfg = json.loads((path / "config.json").read_text()); tc = cfg.get("text_config", cfg)
E = tc.get("num_experts") or tc.get("num_local_experts") or 0
k = tc.get("num_experts_per_tok") or 0
tied = bool(cfg.get("tie_word_embeddings", tc.get("tie_word_embeddings", False)))

total = vision = embed = expert = 0
for f in sorted(path.glob("*.safetensors")):
    with f.open("rb") as fh:
        header = json.loads(fh.read(struct.unpack("<Q", fh.read(8))[0]))
    for name, meta in header.items():
        if name == "__metadata__":
            continue
        size = meta["data_offsets"][1] - meta["data_offsets"][0]
        total += size
        if "vision" in name or "visual" in name:
            vision += size
        elif "embed_tokens" in name:
            embed += size
        elif "switch_mlp" in name or ".experts." in name:
            expert += size

per_token = total - vision - (0 if tied else embed)
if E:
    per_token -= expert * (1 - k / E)
print(f"{repo}: disk {total/1e9:.3f} GB, vision {vision/1e9:.3f}, embed {embed/1e9:.3f} ({'tied' if tied else 'untied'}), "
      f"experts {expert/1e9:.3f} at {k}/{E} -> {per_token/1e9:.3f} GB per token")
for bw in (638, 391, 740, 97):
    print(f"   ceiling at {bw} GB/s: {bw*1e9/per_token:7.1f} tok/s")