Gemma 4 E2B benchmark on an M1 Max · 64 GB

{
  "runId": "run_d3d6f9d6-aa6b-4311-b293-6e3a94e691fa",
  "bundleId": "mlx-gemma-4-e2b-8bit-c19431",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "753787f"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.2",
    "buildFlags": null
  },
  "model": {
    "displayName": "Gemma 4 E2B",
    "format": "mlx",
    "quant": "8bit",
    "architecture": "gemma4",
    "source": "mlx-community/gemma-4-e2b-8bit",
    "fileSizeBytes": 5899567778,
    "lab": {
      "name": "Google",
      "slug": "google"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M1 Max",
    "cpuCores": 10,
    "gpu": "Apple M1 Max",
    "gpuCores": 32,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "15.6.1"
  },
  "decodeTpsMean": 68.7,
  "prefillTpsMean": 1939.8,
  "ttftP50Ms": 2057.9,
  "idleTpsMean": 5185,
  "peakRssMb": 6305,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.858808572126116,
  "bundleSha256": "ad16d5e2fc8e29e88c3316d5c3e1b7eb973b00f79601942631894df3107d4211",
  "createdAt": "2026-04-14T15:19:25.973Z"
}