Gemma 4 E2B IT benchmark on an A18 Pro · 8 GB

{
  "runId": "run_06d08b0e-a1a3-417b-bc9c-f02267c6e60e",
  "bundleId": "llamacpp-gemma-4-e2b-it-q4_k_m.gguf-c269e1",
  "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 E2B IT",
    "format": "gguf",
    "quant": "q4_k_m",
    "architecture": "gemma4",
    "source": "unsloth/gemma-4-E2B-it-GGUF:gemma-4-E2B-it-Q4_K_M.gguf",
    "fileSizeBytes": 3106735776,
    "lab": {
      "name": "Google",
      "slug": "google"
    },
    "quantizedBy": {
      "name": "Unsloth",
      "slug": "unsloth"
    }
  },
  "device": {
    "cpu": "Apple A18 Pro",
    "cpuCores": 6,
    "gpu": "Apple A18 Pro",
    "gpuCores": 5,
    "gpuCount": 1,
    "ramGb": 8,
    "osName": "macOS",
    "osVersion": "26.3.2"
  },
  "decodeTpsMean": 13.1,
  "prefillTpsMean": 194.9,
  "ttftP50Ms": 21063.67,
  "idleTpsMean": 0,
  "peakRssMb": 270.7,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.5424630998883928,
  "bundleSha256": "ed9e678bb9cdf0a5c0118e58f84f03177f56b2fee62e02c9cc5e276ad43f97c9",
  "createdAt": "2026-04-11T05:15:34.032Z"
}