Gemma 4 31B IT benchmark on an M4 Pro · 64 GB

{
  "runId": "run_414346ca-afa9-47b6-a3ba-a618f4c0d296",
  "bundleId": "mlx-gemma-4-31b-it-8bit-cce518",
  "status": "verified",
  "promptTokens": 1536,
  "completionTokens": 768,
  "contextLength": 768,
  "harness": {
    "version": "0.1.20",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.2",
    "buildFlags": null
  },
  "model": {
    "displayName": "Gemma 4 31B IT",
    "format": "mlx",
    "quant": "8bit",
    "architecture": "gemma4",
    "source": "mlx-community/gemma-4-31b-it-8bit",
    "fileSizeBytes": 33763120491,
    "lab": {
      "name": "Google",
      "slug": "google"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M4 Pro",
    "cpuCores": 14,
    "gpu": "Apple M4 Pro",
    "gpuCores": 20,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.3"
  },
  "decodeTpsMean": 7.2,
  "prefillTpsMean": 100.7,
  "ttftP50Ms": 5024.83,
  "idleTpsMean": 32768,
  "peakRssMb": 33792,
  "trialsPassed": 3,
  "trialsTotal": 3,
  "runnabilityScore": 0.23379285714285714,
  "bundleSha256": "227324c180d729838ce832774e64ad7e4fd0be031b80bc0531f5658105a9056a",
  "createdAt": "2026-04-14T03:35:41.761Z"
}