Qwen3-32B benchmark on an M3 Ultra · 256 GB

{
  "runId": "run_f717404d-1182-492f-93fd-1d2085a61c79",
  "bundleId": "mlx-qwen3-32b-4bit-5d987a",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.18",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.1",
    "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 M3 Ultra",
    "cpuCores": 28,
    "gpu": "Apple M3 Ultra",
    "gpuCores": 60,
    "gpuCount": 1,
    "ramGb": 256,
    "osName": "macOS",
    "osVersion": "26.4"
  },
  "decodeTpsMean": 29.6,
  "prefillTpsMean": 255.3,
  "ttftP50Ms": 16045.38,
  "idleTpsMean": 19456,
  "peakRssMb": 20480,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.6389345238095238,
  "bundleSha256": "afbe6dff7ce8ee2b4164e2cfe7d10da0a6a1cc2942c0609bd0be5d1fdffb3ea7",
  "createdAt": "2026-04-05T00:03:12.045Z"
}