Gemma 4 31B benchmark on an M5 Pro · 64 GB

{
  "runId": "run_4653634b-03f0-46ea-95f1-d20a77194c2a",
  "bundleId": "mlx-gemma-4-31b-mxfp4-d09d2a",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.22",
    "gitSha": "ff1d570"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.3",
    "buildFlags": null
  },
  "model": {
    "displayName": "Gemma 4 31B",
    "format": "mlx",
    "quant": "mxfp4",
    "architecture": "gemma4",
    "source": "mlx-community/gemma-4-31b-mxfp4",
    "fileSizeBytes": 17452518872,
    "lab": {
      "name": "Google",
      "slug": "google"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M5 Pro",
    "cpuCores": 18,
    "gpu": "Apple M5 Pro",
    "gpuCores": 20,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.4.1"
  },
  "decodeTpsMean": 14.6,
  "prefillTpsMean": 364.6,
  "ttftP50Ms": 11204.42,
  "idleTpsMean": 142,
  "peakRssMb": 22528,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.4515119047619047,
  "bundleSha256": "0d0aa399a6d466718b897f5b878c87a51302a95053d339a3e8fc6717c0b415ba",
  "createdAt": "2026-05-14T01:03:24.063Z"
}