{
  "image": "ghcr.io/ggml-org/llama.cpp:server-cuda",
  "container_name": "ix-llamacpp-llamacpp-1",
  "host_port": 8071,
  "container_port": 8080,
  "web_ui_url": "http://0.0.0.0:8071/",
  "model_host_path": "/mnt/fast.storage.rushg.me/datasets/apps/llama-cpp.models",
  "model_container_path": "/models",
  "models": [
    "GPT-OSS",
    "Meta-Llama-3-8B-Instruct.Q4_K_M.gguf",
    "openassistant-llama2-13b-orca-8k-3319.Q5_K_M.gguf",
    "Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf"
  ],
  "network": "ix-llamacpp_default",
  "subnets": [
    "172.16.18.0/24",
    "fdb7:86ec:b1dd:11::/64"
  ],
  "gpu_count": 2,
  "gpu_name": "NVIDIA RTX 5060 Ti, 16 GB each (per `nvidia-smi` in prior runs)."
}