{
  "schemaVersion": 1,
  "executedAt": "2026-10-03T18:24:04.647416+00:00",
  "purpose": "Read-only command checks on one Mac; not an inference, memory-fit, or performance experiment",
  "verification": "diagnostic-commands-verified",
  "commands": [
    {
      "command": ["sw_vers"],
      "exitCode": 0,
      "stdout": "ProductName:\t\tmacOS\nProductVersion:\t\t27.0.1\nBuildVersion:\t\t26A434",
      "stderr": ""
    },
    {
      "command": ["sysctl", "hw.memsize"],
      "exitCode": 0,
      "stdout": "hw.memsize: 25769803776",
      "stderr": ""
    },
    {
      "command": ["sysctl", "machdep.cpu.brand_string"],
      "exitCode": 0,
      "stdout": "machdep.cpu.brand_string: Apple M5",
      "stderr": ""
    },
    {
      "command": ["sysctl", "vm.swapusage"],
      "exitCode": 0,
      "stdout": "vm.swapusage: total = 10240.00M  used = 9186.81M  free = 1053.19M  (encrypted)",
      "stderr": ""
    },
    {
      "command": ["vm_stat"],
      "exitCode": 0,
      "stdout": "Mach Virtual Memory Statistics: (page size of 16384 bytes)\nPages free:                                   145342.\nPages active:                                 288793.\nPages inactive:                               285480.\nPages speculative:                              2994.\nPages throttled:                                   0.\nPages wired down:                             239408.\nPages purgeable:                                1797.\n\"Translation faults\":                     2729833185.\nPages copy-on-write:                       225076257.\nPages zero filled:                        2999443782.\nPages reactivated:                         379799520.\nPages purged:                               29822666.\nFile-backed pages:                            255537.\nAnonymous pages:                              321730.\nPages stored in compressor:                   988799.\nPages occupied by compressor:                 557455.\nDecompressions:                            361101848.\nCompressions:                              425658400.\nPageins:                                   133165326.\nPageouts:                                    1940365.\nSwapins:                                     7146306.\nSwapouts:                                   10015435.\nPages tagged:                                 133952.\nPages tagged resident:                        115702.\nPages tagged compressed:                       18250.\nPages tag-storage:                             49152.\nPages tag-storage holding tags:                 5540.\nPages tag-storage free:                          454.\nPages tag-storage non-tag pageable:            42992.\nPages tag-storage non-tag wired:                  88.\nBytes of compressed tags:                    2741952.\nTagged compressions:                         7145698.\nTagged decompressions:                       6768187.",
      "stderr": ""
    },
    {
      "command": ["memory_pressure", "-Q"],
      "exitCode": 0,
      "stdout": "The system has 25769803776 (1572864 pages with a page size of 16384).\nSystem-wide memory free percentage: 47%",
      "stderr": ""
    },
    {
      "command": ["llama-server", "--version"],
      "exitCode": 0,
      "stdout": "",
      "stderr": "version: 0.1.1-dev (build 10470, commit 34af94cd9)\nbuilt with AppleClang 21.0.0.21000101 for Darwin arm64"
    }
  ],
  "runtimeHelp": {
    "exitCode": 0,
    "supportedOptions": ["--ctx-size", "--parallel", "--cache-ram", "--host", "--port"],
    "excerpts": [
      "-c,    --ctx-size N                     size of the prompt context (default: 0, 0 = loaded from model)",
      "                                        (env: LLAMA_ARG_CTX_SIZE)",
      "-n,    --predict, --n-predict N         number of tokens to predict (default: -1, -1 = infinity)",
      "-cram, --cache-ram N                    set the maximum cache size in MiB (default: 8192, -1 - no limit, 0 -",
      "                                        disable)[(more",
      "                                        info)](https://github.com/ggml-org/llama.cpp/pull/16391)",
      "-np,   --parallel N                     number of server slots (default: -1, -1 = auto)",
      "                                        (env: LLAMA_ARG_N_PARALLEL)",
      "-cb,   --cont-batching, -nocb, --no-cont-batching",
      "--host HOST                             ip address to listen, or bind to an UNIX socket if the address ends",
      "                                        with .sock (default: 127.0.0.1)",
      "                                        (env: LLAMA_ARG_HOST)",
      "--port PORT                             port to listen (default: 8080)",
      "                                        (env: LLAMA_ARG_PORT)",
      "--reuse-port                            allow multiple sockets to bind to the same port (default: disabled)"
    ]
  },
  "conditions": {
    "backgroundWorkControlled": false,
    "newModelLoaded": false,
    "existingProcessesChanged": false,
    "runtimeInstalledOrUpdated": false,
    "modelDownloaded": false,
    "pressureGraphObserved": false
  },
  "limits": [
    "No cause is attributed to the observed system-wide swap.",
    "CLI free-memory percentage is not the Activity Monitor memory-pressure graph or an LLM memory budget.",
    "No startup command was rerun; the same-runtime September 5 smoke record supports its historical successful execution.",
    "No optimal context size, throughput improvement, peak memory or model quality was measured."
  ]
}