[Unit]
Description=llama.cpp (PrismML build 10777) Ternary-Bonsai-2-9B PQ2_0-MTP GGUF + refusal adapter (qwen35 hybrid, 3x200704 slots over one 602112 pool, f16 K + q8_0 V, MTP armed, mmproj Q8_0 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
# llama.cpp can take longer than systemd's 90 s default to drain slots and
# release the card: a real stop on 2026-10-18 hit `State 'stop-sigterm' timed
# out. Killing.` and left the unit in `failed` (result 'timeout') even though
# the process had served health correctly. The engine is SIGKILL-safe (nothing
# on disk), but a unit that always ends `failed` is a false alarm for the next
# operator, so give the drain room.
TimeoutStopSec=180
Restart=on-failure
RestartSec=10

[Install]
WantedBy=multi-user.target