[Unit]
Description=llama.cpp DFlash+MTP Inference Server (Qwen3.6-27B on ROCm)
After=network.target

[Service]
Type=simple
User=dank
Group=dank
ExecStart=/home/dank/llama.cpp/build/bin/llama-server --hf-repo unsloth/Qwen3.6-27B-MTP-GGUF:Q8_0 --spec-draft-hf Alittlehammmer/Qwen3.6-27B-DFlash-GGUF-llama.cpp:Q8_0 --spec-type draft-dflash,ngram-mod --spec-draft-n-max 16 --device ROCm0 --spec-draft-device ROCm0 --gpu-layers all --fit on --fit-target 512 --parallel 3 --ctx-size 131072 --batch-size 4096 --port 8080 --host 0.0.0.0 --threads 16 --load-mode none
Restart=on-failure
RestartSec=10

[Install]
WantedBy=multi-user.target