Gemma 4 12B IT benchmark on an M5 Pro · 64 GB

{
  "runId": "run_ac8fd2ba-6c3c-45e3-a6f6-3f88758d9e31",
  "bundleId": "llamacpp-gemma-4-12b-it-q4_0.gguf-c4e625",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.22",
    "gitSha": "50c24e0"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b8920",
    "buildFlags": "metal"
  },
  "model": {
    "displayName": "Gemma 4 12B IT",
    "format": "gguf",
    "quant": "q4_0",
    "architecture": "gemma4",
    "source": "unsloth/gemma-4-12b-it-GGUF:gemma-4-12b-it-Q4_0.gguf",
    "fileSizeBytes": 6738474400,
    "lab": {
      "name": "Google",
      "slug": "google"
    },
    "quantizedBy": {
      "name": "Unsloth",
      "slug": "unsloth"
    }
  },
  "device": {
    "cpu": "Apple M5 Pro",
    "cpuCores": 18,
    "gpu": "Apple M5 Pro",
    "gpuCores": 20,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.5.1"
  },
  "decodeTpsMean": 35.3,
  "prefillTpsMean": 751.5,
  "ttftP50Ms": 5441.29,
  "idleTpsMean": 4556.8,
  "peakRssMb": 4733.4,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.7330460205078124,
  "bundleSha256": "0a51869b41a1245b944832836b6df41c4265f89e4f8b24408fef8bacc98b4566",
  "createdAt": "2026-06-06T16:06:07.922Z"
}