Qwen3.6-27B benchmark on an M4 Pro · 64 GB

{
  "runId": "run_0aa94e01-7b17-4425-805f-1a0ab6ee4b93",
  "bundleId": "mlx-qwen3.6-27b-ud-q8_k_xl-mlx-d74a94",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.20",
    "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": "Brooooooklyn/Qwen3.6-27B-UD-Q8_K_XL-mlx",
    "fileSizeBytes": 31410731381,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M4 Pro",
    "cpuCores": 14,
    "gpu": "Apple M4 Pro",
    "gpuCores": 20,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.3"
  },
  "decodeTpsMean": 8,
  "prefillTpsMean": 113.3,
  "ttftP50Ms": 36161.07,
  "idleTpsMean": 264,
  "peakRssMb": 33792,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.25134285714285715,
  "bundleSha256": "c5a1eea55fdbceefc2ba8e5f766420d838ee71be715778a76cb7a83afe7e13fa",
  "createdAt": "2026-04-26T12:13:46.293Z"
}