Qwen3-32B benchmark on an M4 Max · 128 GB

{
  "runId": "run_60412672-cae1-4767-a8b3-4ffef7396de6",
  "bundleId": "mlx-qwen3-32b-4bit-483ab2",
  "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": "Qwen3-32B",
    "format": "mlx",
    "quant": "4bit",
    "architecture": "qwen3",
    "source": "mlx-community/Qwen3-32B-4bit",
    "fileSizeBytes": 18429850874,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "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": 18.9,
  "prefillTpsMean": 147.3,
  "ttftP50Ms": 27742.03,
  "idleTpsMean": 19456,
  "peakRssMb": 20480,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.5299607142857143,
  "bundleSha256": "c04e8d6bd2b8ef00faf6fcff65149f2072deebeb73b5165b7579d2fc39dd1d10",
  "createdAt": "2026-04-01T00:41:03.309Z"
}