Qwen3.6-27B benchmark on an M1 Max · 64 GB

{
  "runId": "run_ed1fc7e1-ba5b-4c8f-9f07-80237a2594e7",
  "bundleId": "mlx-qwen3.6-27b-8bit-6810ec",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.3",
    "buildFlags": null
  },
  "model": {
    "displayName": "Qwen3.6-27B",
    "format": "mlx",
    "quant": "8bit",
    "architecture": "qwen3_5",
    "source": "mlx-community/Qwen3.6-27B-8bit",
    "fileSizeBytes": 29501218261,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M1 Max",
    "cpuCores": 10,
    "gpu": "Apple M1 Max",
    "gpuCores": 32,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.3.1"
  },
  "decodeTpsMean": 11.3,
  "prefillTpsMean": 90.4,
  "ttftP50Ms": 45322.77,
  "idleTpsMean": 5025,
  "peakRssMb": 31744,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.3067107142857143,
  "bundleSha256": "a4af88be2d6b3890903301c0578fd74fd7ff82eafa6ff408c3efd309ccc0c368",
  "createdAt": "2026-05-09T01:16:59.542Z"
}