Gemma 4 31B IT benchmark on an M5 Max · 64 GB

{
  "runId": "run_517ef47b-9407-426c-aeb3-0904466a3588",
  "bundleId": "mlx-gemma-4-31b-it-4bit-83d1be",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.3",
    "buildFlags": null
  },
  "model": {
    "displayName": "Gemma 4 31B IT",
    "format": "mlx",
    "quant": "4bit",
    "architecture": "gemma4",
    "source": "mlx-community/gemma-4-31b-it-4bit",
    "fileSizeBytes": 18412016832,
    "lab": {
      "name": "Google",
      "slug": "google"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M5 Max",
    "cpuCores": 18,
    "gpu": "Apple M5 Max",
    "gpuCores": 40,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.5"
  },
  "decodeTpsMean": 19.1,
  "prefillTpsMean": 440.2,
  "ttftP50Ms": 9430.07,
  "idleTpsMean": 18432,
  "peakRssMb": 23552,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.49791547619047616,
  "bundleSha256": "4348d86b5b18200bc6f4fc823354403a8aceee8a56ec83f2183aba79b891d11a",
  "createdAt": "2026-04-24T19:32:17.367Z"
}