Llama 3.2 3B Instruct benchmark on an M4 Max · 128 GB

{
  "runId": "run_61a6ee75-44af-4e34-a865-df357854f10f",
  "bundleId": "mlx-llama-3.2-3b-instruct-4bit-9243bc",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.18",
    "gitSha": "c71d7d8"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.2",
    "buildFlags": null
  },
  "model": {
    "displayName": "Llama 3.2 3B Instruct",
    "format": "mlx",
    "quant": "4bit",
    "architecture": "llama",
    "source": "mlx-community/Llama-3.2-3B-Instruct-4bit",
    "fileSizeBytes": 1807496278,
    "lab": {
      "name": "Meta",
      "slug": "meta"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M4 Max",
    "cpuCores": 16,
    "gpu": "Apple M4 Max",
    "gpuCores": 40,
    "gpuCount": 1,
    "ramGb": 128,
    "osName": "macOS",
    "osVersion": "26.4"
  },
  "decodeTpsMean": 160.1,
  "prefillTpsMean": 1548.1,
  "ttftP50Ms": 2669.74,
  "idleTpsMean": 2661,
  "peakRssMb": 3725,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.9152252165876116,
  "bundleSha256": "146e7961e75e0e56fc7d556fbc174eda5617a72856d9e69a0602ef9c27fa778e",
  "createdAt": "2026-03-31T16:41:08.157Z"
}