@echo off
echo =========================================================
echo  Qwen3.5 35B-A3B API Server (MoE Optimized)
echo  [INFO] --cpu-moe: Expert weights forced to CPU RAM
echo  [INFO] -ngl 999: All attention layers on GPU
echo  [INFO] -np 1: Single slot for max speed
echo =========================================================
echo.
llama_bin_run\llama-server.exe --model models\Qwen3.5-35B-A3B-Q4_K_M.gguf -ngl 999 --cpu-moe -c 4096 -np 1 -fa on --cache-type-k q4_0 --cache-type-v q4_0 -ub 512 -b 2048 -t 6 --mlock --prio 2 --port 8000 --host 0.0.0.0
pause