양자화는 공간과 속도를 함께 사

#!/usr/bin/env python3
"""Effective bits per weight of a quantized checkpoint, from the safetensors
headers: packed uint32 weights hold 32/bits values each; the scales and biases
per group are the overhead that turns 4 bits into ~4.5."""
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/Qwen3.5-27B-4bit"
path = Path(snapshot_download(repo, local_files_only=True))
cfg = json.loads((path / "config.json").read_text())
q = cfg.get("quantization") or cfg.get("text_config", {}).get("quantization") or {}
bits = q.get("bits", 16)

params = bytes_total = 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
        n = 1
        for d in meta["shape"]:
            n *= d
        bytes_total += meta["data_offsets"][1] - meta["data_offsets"][0]
        if name.endswith(".weight") and meta["dtype"] == "U32":
            params += n * (32 // bits)          # packed quantized weights
        elif name.endswith((".scales", ".biases")):
            pass                                # quantization overhead: bytes, not weights
        else:
            params += n                          # unquantized tensors (norms, some embeddings)

print(f"{repo}: {q or 'unquantized'}")
print(f"  parameters {params/1e9:.2f} B, file {bytes_total/1e9:.2f} GB -> {bytes_total*8/params:.2f} bits per weight overall")
print(f"  bf16 would be {params*2/1e9:.1f} GB; this file is {params*2/bytes_total:.2f}x smaller -> ceiling {params*2/bytes_total:.2f}x higher")

# office, 2026-09-15:
# Qwen3.5-27B-4bit: 27.36 B params, 16.05 GB -> 4.69 bits/weight; bf16 54.7 GB; 3.41x
# Qwen3.5-9B-4bit:   9.41 B params,  5.95 GB -> 5.06 bits/weight; bf16 18.8 GB; 3.16x
# Llama-3.2-1B-4bit: 1.24 B params,  0.70 GB -> 4.50 bits/weight; bf16  2.5 GB; 3.56x