Gemma 4 26B A4B IT benchmark on an M4 Pro · 48 GB

{
  "runId": "run_3c362c04-0067-4316-92e5-02cf135b2b4e",
  "bundleId": "llamacpp-gemma-4-26b-a4b-it-q4_k_m.gguf-932135",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "b88df72"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b8950",
    "buildFlags": "metal"
  },
  "model": {
    "displayName": "Gemma 4 26B A4B IT",
    "format": "gguf",
    "quant": "q4_k_m",
    "architecture": "gemma4",
    "source": "ggml-org/gemma-4-26B-A4B-it-GGUF:gemma-4-26B-A4B-it-Q4_K_M.gguf",
    "fileSizeBytes": 16796015136,
    "lab": {
      "name": "Google",
      "slug": "google"
    },
    "quantizedBy": {
      "name": "ggml",
      "slug": "ggml"
    }
  },
  "device": {
    "cpu": "Apple M4 Pro",
    "cpuCores": 14,
    "gpu": "Apple M4 Pro",
    "gpuCores": 20,
    "gpuCount": 1,
    "ramGb": 48,
    "osName": "macOS",
    "osVersion": "26.0.1"
  },
  "decodeTpsMean": 54.9,
  "prefillTpsMean": 649.8,
  "ttftP50Ms": 6259.64,
  "idleTpsMean": 6722.9,
  "peakRssMb": 10380.3,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.706820966796875,
  "bundleSha256": "56f18e0e07bcf7a9d27d5f3f2d0949852fdabac1fb9d2128692180e46fd87651",
  "createdAt": "2026-04-28T08:02:39.032Z"
}