[Unit]
Description=llama.cpp Qwen3.8-27B Uncensored UD-Q8_K_XL + DFlash2 drafter (dankserver, frank-medium, 2x Radeon AI PRO R9700)
After=network-online.target
Wants=network-online.target

[Service]
Type=simple
User=dank
Group=dank
# The engine pins staging buffers on the first card; keep the memlock budget
# unbounded so an RLIMIT that is smaller than the split buffers cannot fail the
# load.  Parity with the other LLM units on this fleet.
LimitMEMLOCK=infinity
Environment="FRANK_MEDIUM_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-medium.env"
ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-medium.sh
Restart=on-failure
RestartSec=10

[Install]
WantedBy=multi-user.target