[Unit]
Description=Qwen3.5-9B llama-server-turbo
After=network-online.target
Wants=network-online.target

[Service]
Type=simple
User=root
WorkingDirectory=/models/llm/uncensored
ExecStart=/usr/local/bin/llama-server-turbo \
  -m /models/llm/uncensored/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf \
  --port 8082 \
  --host 0.0.0.0 \
  --cache-type-k turbo4 \
  --cache-type-v turbo4 \
  -ngl 99 \
  --no-mmap \
  --mlock \
  --jinja \
  --prio 2 \
  --poll 80 \
  --cont-batching \
  --timeout 300 \
  -c 128000 \
  --ctx-size 128000 \
  --threads 16 \
  --threads-batch 32 \
  --parallel 1 \
  --batch-size 4096 \
  --ubatch-size 1024 \
  --temp 0.2 \
  --top-p 0.95 \
  --min-p 0.05 \
  --top-k 20 \
  --metrics
Restart=on-failure
RestartSec=5
LimitMEMLOCK=infinity
LimitNOFILE=1048576

[Install]
WantedBy=multi-user.target