Gemma 4 E4B IT benchmark on an M5 Pro · 48 GB

{
  "runId": "run_64314e29-a810-41ed-b1c1-c60f2055d0fb",
  "bundleId": "llamacpp-gemma-4-e4b-it-q4_k_m.gguf-8a1a8a",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.20",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b8680",
    "buildFlags": "metal"
  },
  "model": {
    "displayName": "Gemma 4 E4B IT",
    "format": "gguf",
    "quant": "q4_k_m",
    "architecture": "gemma4",
    "source": "unsloth/gemma-4-E4B-it-GGUF:gemma-4-E4B-it-Q4_K_M.gguf",
    "fileSizeBytes": 4977169088,
    "lab": {
      "name": "Google",
      "slug": "google"
    },
    "quantizedBy": {
      "name": "Unsloth",
      "slug": "unsloth"
    }
  },
  "device": {
    "cpu": "Apple M5 Pro",
    "cpuCores": 15,
    "gpu": "Apple M5 Pro",
    "gpuCores": 16,
    "gpuCount": 1,
    "ramGb": 48,
    "osName": "macOS",
    "osVersion": "26.4.1"
  },
  "decodeTpsMean": 65.7,
  "prefillTpsMean": 1429.8,
  "ttftP50Ms": 2861.97,
  "idleTpsMean": 5392.9,
  "peakRssMb": 6909.4,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.8097948130580357,
  "bundleSha256": "65c3610a5b0564b3816e6aecee7bc5773752a10a748dc9006e6507f9add2b363",
  "createdAt": "2026-04-13T17:54:04.258Z"
}