Gemopus 4 E4B IT benchmark on an M4 Max · 36 GB

{
  "runId": "run_1d213b79-4d13-4590-b2f1-609b6df1cc4b",
  "bundleId": "llamacpp-gemma-4-e4b-it.q8_0.gguf-ee138d",
  "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": "Gemopus 4 E4B IT",
    "format": "gguf",
    "quant": "q8_0",
    "architecture": "gemma4",
    "source": "Jackrong/Gemopus-4-E4B-it-GGUF:gemma-4-E4B-it.Q8_0.gguf",
    "fileSizeBytes": 8031225280,
    "lab": {
      "name": "Jackrong",
      "slug": "jackrong"
    },
    "quantizedBy": {
      "name": "Jackrong",
      "slug": "jackrong"
    }
  },
  "device": {
    "cpu": "Apple M4 Max",
    "cpuCores": 14,
    "gpu": "Apple M4 Max",
    "gpuCores": 32,
    "gpuCount": 1,
    "ramGb": 36,
    "osName": "macOS",
    "osVersion": "15.6.1"
  },
  "decodeTpsMean": 54.4,
  "prefillTpsMean": 1180.2,
  "ttftP50Ms": 3470.86,
  "idleTpsMean": 8399.7,
  "peakRssMb": 8446.7,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.7424108277529762,
  "bundleSha256": "526b7044db9dec3c7fae1c6b296b5fe5b89ca2de386701df00eceae139989023",
  "createdAt": "2026-04-11T08:15:51.097Z"
}