Gemma 4 26B A4B IT benchmark on an M4 Max · 64 GB

{
  "runId": "run_2bcda913-1e1c-444b-86db-0604c600c27e",
  "bundleId": "mlx-gemma-4-26b-a4b-it-qat-mlx-4bit-aca01a",
  "status": "verified",
  "promptTokens": 12288,
  "completionTokens": 3072,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.3",
    "buildFlags": null
  },
  "model": {
    "displayName": "Gemma 4 26B A4B IT",
    "format": "mlx",
    "quant": "4bit",
    "architecture": "gemma4",
    "source": "lmstudio-community/gemma-4-26B-A4B-it-QAT-MLX-4bit",
    "fileSizeBytes": 15608838574,
    "lab": {
      "name": "Google",
      "slug": "google"
    },
    "quantizedBy": {
      "name": "LM Studio",
      "slug": "lmstudio"
    }
  },
  "device": {
    "cpu": "Apple M4 Max",
    "cpuCores": 16,
    "gpu": "Apple M4 Max",
    "gpuCores": 40,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.5.1"
  },
  "decodeTpsMean": 100.8,
  "prefillTpsMean": 1230.7,
  "ttftP50Ms": 3325.28,
  "idleTpsMean": 15360,
  "peakRssMb": 17408,
  "trialsPassed": 3,
  "trialsTotal": 3,
  "runnabilityScore": 0.7976957142857142,
  "bundleSha256": "f1482d91a68e25ff9770d9a67d1896bd31107b927d4782bec497c8a94ebdf8ba",
  "createdAt": "2026-06-21T00:15:27.486Z"
}