Gemma 4 E2B benchmark on an M1 Max · 64 GB

{
  "runId": "run_5b30a23d-335d-43af-81d0-de7191646984",
  "bundleId": "mlx-gemma-4-e2b-mxfp4-b2492f",
  "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": "mxfp4",
    "architecture": "gemma4",
    "source": "mlx-community/gemma-4-e2b-mxfp4",
    "fileSizeBytes": 4263396466,
    "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": 70.6,
  "prefillTpsMean": 1965.1,
  "ttftP50Ms": 2138.99,
  "idleTpsMean": 1272,
  "peakRssMb": 4731,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.8732167152622767,
  "bundleSha256": "c32bde7eab7df82f9ef6f0942fa7922dd7e2e7806a27f2907a9c276a5acee3fd",
  "createdAt": "2026-04-14T15:29:10.083Z"
}