기계 하나에 들어가도록 양자화하기

#!/usr/bin/env python3
"""Quantize to fit one machine. The bits ladder measured on a small checkpoint on office
(one command, seconds), then the same arithmetic applied to the store's big files. The
store is not a quantizer; this runs on a Mac that is."""
import subprocess, sys
# --- the command, run for real on a 1B so its cost is known (office, 2026-09-15, mlx-lm 0.31.3) ---
# python -m mlx_lm convert --hf-path unsloth/Llama-3.2-1B-Instruct --mlx-path q4-llama -q --q-bits 4 --q-group-size 64
# bf16 2.47 GB -> 3 bits: 532 MB (3.501 b/w), 461.7 tok/s | 4 bits: 680 MB (4.501), 428.6 | 6 bits: 974 MB (6.501), 330.1
#                        8 bits: 1.2 GB (8.500), 292.2 | bf16 as shipped: 187.8 tok/s.  3 s per conversion.
BW, WS = 819.0, 498.0
STORE = [("GLM-5.3", 753, 1506.7), ("GLM-5.3-Flash", 320, 642.7), ("Kimi K3", 2800, 1561.0), ("Qwen3.8-Flash-Next", 180, 360.0)]
print(f"{'checkpoint':20} {'params B':>8} {'bf16 GB':>8} | " + " ".join(f"{b}-bit GB" for b in (8, 6, 4, 3)) + "   fits 498 at")
for name, params, bf16 in STORE:
    sizes = {b: params * (b + 0.5) / 8 for b in (8, 6, 4, 3)}                     # b bits + ~0.5 for scales/biases at group 64
    fits = next((f"{b} bits" for b in (8, 6, 4, 3) if sizes[b] + 16 <= WS), "nothing")
    print(f"{name:20} {params:8d} {bf16:8.0f} | " + " ".join(f"{sizes[b]:8.0f}" for b in (8, 6, 4, 3)) + f"   {fits}")
print("\nreading the 1.5 TB original once at the Air's measured 2.85 GB/s is ~9 minutes; a Studio SSD is faster and unmeasured here.")
print("whether the converter needs the whole BF16 set resident at once on a 512 GB Mac was not tested on a 1.5 TB input -- the 2.5 GB one fit trivially.")