Gemma 4 E4B benchmark on an M5 · 32 GB

{
  "runId": "run_35a2fcee-cfb9-4c05-a4d2-a79addf010e4",
  "bundleId": "mlx-gemma-4-e4b-8bit-d2c372",
  "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 E4B",
    "format": "mlx",
    "quant": "8bit",
    "architecture": "gemma4",
    "source": "mlx-community/gemma-4-e4b-8bit",
    "fileSizeBytes": 8965298732,
    "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": 22.2,
  "prefillTpsMean": 1532.1,
  "ttftP50Ms": 2835.81,
  "idleTpsMean": 937,
  "peakRssMb": 9733,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.6292074623325892,
  "bundleSha256": "2148672dcd722c7b68a1e62f70ef4a1813eeb6b6a85d18f2d49c2de554a22df7",
  "createdAt": "2026-04-17T12:12:46.489Z"
}