@echo off
chcp 65001 >nul
echo =========================================================
echo  Qwen3.5 122B-A10B API Server (Final Optimized)
echo  [CORE] --cpu-moe + -ngl 999: WDDM swap 완전 회피
echo  [TUNED] -t 4: CPU 캐시 경합 최소화 (10.83 t/s)
echo  [TUNED] mmap on: 메모리 매핑 활성 (no-mmap보다 빠름)
echo  [VRAM] 5.4GB / 12GB (54%% 여유)
echo =========================================================
echo.

llama_bin_run\llama-server.exe ^
  --model models\Q4_K_M\Qwen3.5-122B-A10B-Q4_K_M-00001-of-00003.gguf ^
  -ngl 999 ^
  --cpu-moe ^
  -c 2048 ^
  -np 1 ^
  -fa on ^
  --cache-type-k q4_0 ^
  --cache-type-v q4_0 ^
  -ub 256 ^
  -b 1024 ^
  -t 4 ^
  --mlock ^
  --prio 2 ^
  --port 8000 ^
  --host 0.0.0.0

pause