Qwen3.6-35B-A3B benchmark on an M4 Max · 64 GB

{
  "runId": "run_b22a005a-2b37-4024-9b26-a1389b6ea36c",
  "bundleId": "mlx-qwen3.6-35b-a3b-mlx-6bit-726bd9",
  "status": "verified",
  "promptTokens": 12288,
  "completionTokens": 3072,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.1",
    "buildFlags": null
  },
  "model": {
    "displayName": "Qwen3.6-35B-A3B",
    "format": "mlx",
    "quant": "6bit",
    "architecture": "qwen3_5_moe",
    "source": "lmstudio-community/Qwen3.6-35B-A3B-MLX-6bit",
    "fileSizeBytes": 29061803049,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "LM Studio",
      "slug": "lmstudio"
    }
  },
  "device": {
    "cpu": "Apple M4 Max",
    "cpuCores": 16,
    "gpu": "Apple M4 Max",
    "gpuCores": 40,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.5.1"
  },
  "decodeTpsMean": 70.7,
  "prefillTpsMean": 965.9,
  "ttftP50Ms": 4190.31,
  "idleTpsMean": 27648,
  "peakRssMb": 29696,
  "trialsPassed": 3,
  "trialsTotal": 3,
  "runnabilityScore": 0.6584435714285715,
  "bundleSha256": "7d6792eb034f065b36712f72bcbaea74b6831ff7f0349a6fddcb7a2a4b836ed4",
  "createdAt": "2026-06-21T00:15:28.929Z"
}