Gemma 4 E2B IT benchmark on an M4 · 24 GB

{
  "runId": "run_bfd5705c-8f59-4f03-85b7-bd246733ebd1",
  "bundleId": "llamacpp-gemma-4-e2b-it-iq4_nl.gguf-126108",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b8680",
    "buildFlags": "metal"
  },
  "model": {
    "displayName": "Gemma 4 E2B IT",
    "format": "gguf",
    "quant": "iq4_nl",
    "architecture": "gemma4",
    "source": "unsloth/gemma-4-E2B-it-GGUF:gemma-4-E2B-it-IQ4_NL.gguf",
    "fileSizeBytes": 3041081472,
    "lab": {
      "name": "Google",
      "slug": "google"
    },
    "quantizedBy": {
      "name": "Unsloth",
      "slug": "unsloth"
    }
  },
  "device": {
    "cpu": "Apple M4",
    "cpuCores": 10,
    "gpu": "Apple M4",
    "gpuCores": 10,
    "gpuCount": 1,
    "ramGb": 24,
    "osName": "macOS",
    "osVersion": "26.3"
  },
  "decodeTpsMean": 44.5,
  "prefillTpsMean": 664,
  "ttftP50Ms": 6252.7,
  "idleTpsMean": 0,
  "peakRssMb": 881.6,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.7677761160714286,
  "bundleSha256": "3955491261d9d6eb89b4fbe8f86efb63739f6a6908ae592cbd65ea63d1b2b49a",
  "createdAt": "2026-05-05T02:41:06.211Z"
}