Gemma 4 E2B benchmark on an M2 Max · 64 GB

{
  "runId": "run_aa9ef76b-dca5-41f4-9e0e-725474525dfe",
  "bundleId": "mlx-gemma-4-e2b-5bit-2780e7",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "0d899801"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.2",
    "buildFlags": null
  },
  "model": {
    "displayName": "Gemma 4 E2B",
    "format": "mlx",
    "quant": "5bit",
    "architecture": "gemma4",
    "source": "mlx-community/gemma-4-e2b-5bit",
    "fileSizeBytes": 4160719027,
    "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": 64,
    "osName": "macOS",
    "osVersion": "26.3.1"
  },
  "decodeTpsMean": 91.9,
  "prefillTpsMean": 3309.2,
  "ttftP50Ms": 1236.89,
  "idleTpsMean": 1774,
  "peakRssMb": 4863,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.9387785037667411,
  "bundleSha256": "825ff3a6827c1d5bed1eb84c89a4206991ff7e96d74a6aed4044703e0a9014d2",
  "createdAt": "2026-04-15T02:33:01.720Z"
}