Gemma 4 26B A4B IT benchmark on an M2 Max · 32 GB

{
  "runId": "run_8ba03db4-e91d-42c1-8cd4-a55cf2e08520",
  "bundleId": "mlx-gemma-4-26b-a4b-it-nvfp4-49c3f6",
  "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 26B A4B IT",
    "format": "mlx",
    "quant": "nvfp4",
    "architecture": "gemma4",
    "source": "mlx-community/gemma-4-26b-a4b-it-nvfp4",
    "fileSizeBytes": 15608810138,
    "lab": {
      "name": "Google",
      "slug": "google"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M2 Max",
    "cpuCores": 12,
    "gpu": "Apple M2 Max",
    "gpuCores": 30,
    "gpuCount": 1,
    "ramGb": 32,
    "osName": "macOS",
    "osVersion": "26.4.1"
  },
  "decodeTpsMean": 54.9,
  "prefillTpsMean": 488.1,
  "ttftP50Ms": 8453.29,
  "idleTpsMean": 14336,
  "peakRssMb": 16384,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.5660809523809525,
  "bundleSha256": "18138c7c4ca413e8125f7373e7c27d4cd00e3ed5ef49df8c512d42779f0613cf",
  "createdAt": "2026-05-11T22:05:59.851Z"
}