[Unit]
Description=unsloth llama.cpp (b11030-mix, ROCm gfx120X) Qwen3.8-Flash-Next Q8_0, shared-Q8_0 MTP + ngram-mod spec chain, BF16 vision, 262144 ctx / 1 slot, root systemd unit (dankserver, frank-primary, 2x Radeon AI PRO R9700)
After=network-online.target
Wants=network-online.target

[Service]
Type=simple
User=dank
Group=dank
# The model is mmap'd (175 GiB of expert pages + the 51B-param n-gram
# table live in page cache); an RLIMIT_MEMLOCK smaller than what the
# runtime pins would fail the load mid-start. Parity with the other LLM
# units on this fleet.
LimitMEMLOCK=infinity
Environment="FRANK_PRIMARY_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-primary.env"
ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-primary.sh
Restart=on-failure
RestartSec=10

[Install]
WantedBy=multi-user.target