Qwen3.8-27B benchmark on an M5 Pro · 64 GB

{
  "runId": "run_84a150f8-4349-4c59-a68f-8e1f4a08da6b",
  "bundleId": "mlx-qwen3.8-27b-8bit-755835",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.22",
    "gitSha": "50c24e0"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.3",
    "buildFlags": null
  },
  "model": {
    "displayName": "Qwen3.8-27B",
    "format": "mlx",
    "quant": "8bit",
    "architecture": "qwen3_5",
    "source": "mlx-community/Qwen3.8-27B-8bit",
    "fileSizeBytes": 29501218479,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M5 Pro",
    "cpuCores": 18,
    "gpu": "Apple M5 Pro",
    "gpuCores": 20,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.5.2"
  },
  "decodeTpsMean": 9.8,
  "prefillTpsMean": 406.2,
  "ttftP50Ms": 10040.89,
  "idleTpsMean": 2312,
  "peakRssMb": 30720,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.35987380952380954,
  "bundleSha256": "94128c5d1f92b686d3d9a604865bafb3a37a9a47bcd592194c14ec0bf7198d8c",
  "createdAt": "2026-08-15T13:18:19.466Z"
}