Gemma 4 31B benchmark on an M4 Max · 128 GB

{
  "runId": "run_5d095b1d-c849-4909-97f6-69c2a11a9bc1",
  "bundleId": "mlx-gemma-4-31b-8bit-1e1cc5",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.18",
    "gitSha": "c60e6d1"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.2",
    "buildFlags": null
  },
  "model": {
    "displayName": "Gemma 4 31B",
    "format": "mlx",
    "quant": "8bit",
    "architecture": "gemma4",
    "source": "mlx-community/gemma-4-31b-8bit",
    "fileSizeBytes": 33763120491,
    "lab": {
      "name": "Google",
      "slug": "google"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M4 Max",
    "cpuCores": 16,
    "gpu": "Apple M4 Max",
    "gpuCores": 40,
    "gpuCount": 1,
    "ramGb": 128,
    "osName": "macOS",
    "osVersion": "26.4"
  },
  "decodeTpsMean": 12.5,
  "prefillTpsMean": 154.7,
  "ttftP50Ms": 26545.69,
  "idleTpsMean": 32768,
  "peakRssMb": 37888,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.4172910714285714,
  "bundleSha256": "a6cc359a64f59080a7284a366264f9b8e48a1a83e4ee41ed2011b43183e33023",
  "createdAt": "2026-04-04T17:33:19.644Z"
}