Gemma 4 12B IT benchmark on an M4 · 24 GB

{
  "runId": "run_f7757335-1c69-45d5-97f7-62894f20a467",
  "bundleId": "llamacpp-gemma-4-12b-it-q4_0.gguf-696b97",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b9430",
    "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 M4",
    "cpuCores": 10,
    "gpu": "Apple M4",
    "gpuCores": 10,
    "gpuCount": 1,
    "ramGb": 24,
    "osName": "macOS",
    "osVersion": "26.5.1"
  },
  "decodeTpsMean": 13.4,
  "prefillTpsMean": 136,
  "ttftP50Ms": 30562.15,
  "idleTpsMean": 7539.5,
  "peakRssMb": 7671.9,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.41081268136160715,
  "bundleSha256": "b8131509f8a6ec30a6b5dca7aecbd5e7acb15c849897000b3255ad4baebe1e65",
  "createdAt": "2026-06-05T23:53:34.734Z"
}