Ornstein-27B benchmark on an M4 Pro · 64 GB

{
  "runId": "run_585ad451-e51e-4c16-bd54-cb639a27f7e7",
  "bundleId": "llamacpp-ornstein-27b-q4_k_m.gguf-777698",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.18",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b8500",
    "buildFlags": "metal"
  },
  "model": {
    "displayName": "Ornstein-27B",
    "format": "gguf",
    "quant": "q4_k_m",
    "architecture": "qwen35",
    "source": "DJLougen/Ornstein-27B-GGUF:Ornstein-27B-Q4_K_M.gguf",
    "fileSizeBytes": 16547399104,
    "lab": {
      "name": "Dan Lougen",
      "slug": "djlougen"
    },
    "quantizedBy": {
      "name": "Dan Lougen",
      "slug": "djlougen"
    }
  },
  "device": {
    "cpu": "Apple M4 Pro",
    "cpuCores": 14,
    "gpu": "Apple M4 Pro",
    "gpuCores": 20,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.3"
  },
  "decodeTpsMean": 12.1,
  "prefillTpsMean": 120.7,
  "ttftP50Ms": 33813.79,
  "idleTpsMean": 0,
  "peakRssMb": 16593.7,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.4205608136858259,
  "bundleSha256": "5c98a043d300ab5100269cb698a37b5e534795cbc52276bb751fc045ffc8edda",
  "createdAt": "2026-04-08T17:10:08.683Z"
}