Gemma 4 E4B IT benchmark on an M1 · 16 GB

{
  "runId": "run_4a6e4f7b-aa72-47c5-9786-c3cea248116e",
  "bundleId": "mlx-gemma-4-e4b-it-4bit-cb19b1",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.3",
    "buildFlags": null
  },
  "model": {
    "displayName": "Gemma 4 E4B IT",
    "format": "mlx",
    "quant": "4bit",
    "architecture": "gemma4",
    "source": "mlx-community/gemma-4-e4b-it-4bit",
    "fileSizeBytes": 5146800534,
    "lab": {
      "name": "Google",
      "slug": "google"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M1",
    "cpuCores": 8,
    "gpu": "Apple M1",
    "gpuCores": 8,
    "gpuCount": 1,
    "ramGb": 16,
    "osName": "macOS",
    "osVersion": "26.5.2"
  },
  "decodeTpsMean": 13.1,
  "prefillTpsMean": 180.3,
  "ttftP50Ms": 24946.4,
  "idleTpsMean": 4536,
  "peakRssMb": 7685,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.35195135323660715,
  "bundleSha256": "619aeafe1fc7ae84912734f33c7ed4cd2dce5a30e118098bb88ed8be1b68d2d1",
  "createdAt": "2026-08-21T12:56:44.852Z"
}