diff --git a/app/services/search/rerank_service.py b/app/services/search/rerank_service.py
index 877926a..706fe79 100644
--- a/app/services/search/rerank_service.py
+++ b/app/services/search/rerank_service.py
@@ -17,6 +17,7 @@ snippet 생성:
 from __future__ import annotations
 
 import asyncio
+import os
 import re
 from typing import TYPE_CHECKING
 
@@ -33,8 +34,11 @@ logger = setup_logger("rerank")
 # 동시 rerank 호출 제한 (GPU saturation 방지)
 RERANK_SEMAPHORE = asyncio.Semaphore(2)
 
-# rerank input 크기 제한 (latency / VRAM hard cap)
-MAX_RERANK_INPUT = 200
+# rerank input 크기 제한 (latency / VRAM hard cap).
+# 2노드 이관(2026-07-02): env MAX_RERANK_INPUT 로 조정 가능 — 맥미니 llama.cpp 리랭크는
+# 후보 수에 선형(NAS발 실측 50=0.60s / 100=0.95s / 200=1.89s)이라 NAS 배포는 50 권장.
+# 기본 200 = 현행(GPU TEI) 무회귀.
+MAX_RERANK_INPUT = int(os.getenv("MAX_RERANK_INPUT", "200"))
 MAX_CHUNKS_PER_DOC = 2
 
 # Soft timeout (초)