Gemma 4 E2B IT benchmark on an M5 · 32 GB

{
  "runId": "run_95237bc8-6f09-42e6-acae-d0d5b1001532",
  "bundleId": "mlx-gemma-4-e2b-it-4bit-aa8cb6",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.2",
    "buildFlags": null
  },
  "model": {
    "displayName": "Gemma 4 E2B IT",
    "format": "mlx",
    "quant": "4bit",
    "architecture": "gemma4",
    "source": "mlx-community/gemma-4-e2b-it-4bit",
    "fileSizeBytes": 3581101896,
    "lab": {
      "name": "Google",
      "slug": "google"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M5",
    "cpuCores": 10,
    "gpu": "Apple M5",
    "gpuCores": 10,
    "gpuCount": 1,
    "ramGb": 32,
    "osName": "macOS",
    "osVersion": "26.4"
  },
  "decodeTpsMean": 74.8,
  "prefillTpsMean": 5728.3,
  "ttftP50Ms": 715.9,
  "idleTpsMean": 943,
  "peakRssMb": 4495,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.9034100655691965,
  "bundleSha256": "495c293248a4ab042e3ef2e2a2ebd5e36f945e528c547589a927f2ed9fcdb23d",
  "createdAt": "2026-04-17T10:12:20.529Z"
}