[Unit]
Description=llama.cpp Qwen3.5-9B-Uncensored-HauhauCS-Aggressive Q6_K GGUF (qwen35 hybrid, 2x200704 slots, f16 K+V, MTP off, mmproj vision) on the RTX 3090 (dankclaw, frank-zealot)
After=network-online.target
Wants=network-online.target

[Service]
Type=simple
User=dank
Group=dank
# CUDA pins its staging buffers, so the process needs the memlock budget even
# though the weights themselves are copied into VRAM.
LimitMEMLOCK=infinity
Environment="FRANK_ZEALOT_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-zealot.env"
ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-zealot.sh
Restart=on-failure
RestartSec=10

[Install]
WantedBy=multi-user.target