[Unit]
Description=llama.cpp Swift-1.5-Qwen3.8-27B GSQ-RCO IQ3_S-mtp GGUF (qwen35 hybrid, 2x131072 slots, q8_0 K+V, no speculative decoding, mmproj vision) on the RTX 3090 (dankclaw, frank-small)
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_SMALL_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-small.env"
ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-small.sh
Restart=on-failure
RestartSec=10

[Install]
WantedBy=multi-user.target