Gemma 4 E2B benchmark on an M1 Max · 64 GB

{
  "runId": "run_df852c9e-0ce7-4168-b199-e29e6bed14ab",
  "bundleId": "mlx-gemma-4-e2b-nvfp4-855cd1",
  "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": "nvfp4",
    "architecture": "gemma4",
    "source": "mlx-community/gemma-4-e2b-nvfp4",
    "fileSizeBytes": 4359640245,
    "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": 72.9,
  "prefillTpsMean": 2279.7,
  "ttftP50Ms": 1707.97,
  "idleTpsMean": 1121,
  "peakRssMb": 4830,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.8847568066406251,
  "bundleSha256": "cb7c60e71226f8191d8020176bc5008449393590957d3c6fd0dca35d5e660f65",
  "createdAt": "2026-04-14T15:35:15.934Z"
}