Qwen3.6-35B-A3B benchmark on an M5 Max · 64 GB

{
  "runId": "run_5413bb14-36bd-485f-8269-dcb7ec1882de",
  "bundleId": "mlx-qwen3.6-35b-a3b-4bit-dwq-cdc69a",
  "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": "Qwen3.6-35B-A3B",
    "format": "mlx",
    "quant": "4bit-dwq",
    "architecture": "qwen3_5_moe",
    "source": "mlx-community/Qwen3.6-35B-A3B-4bit-DWQ",
    "fileSizeBytes": 20659180849,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M5 Max",
    "cpuCores": 18,
    "gpu": "Apple M5 Max",
    "gpuCores": 40,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.5.2"
  },
  "decodeTpsMean": 110.6,
  "prefillTpsMean": 1817.6,
  "ttftP50Ms": 2244.32,
  "idleTpsMean": 5136,
  "peakRssMb": 22528,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.7935585714285714,
  "bundleSha256": "684e63196fd3d94945b7b5f562eaa735a8e3eaf2dd4149753da77e7a64e937d3",
  "createdAt": "2026-07-23T14:48:59.239Z"
}