Qwen3.6-35B-A3B benchmark on an M4 Pro · 48 GB

{
  "runId": "run_75cf84e2-a8f9-40d4-8bf1-088d29badf8c",
  "bundleId": "mlx-qwen3.6-35b-a3b-4bit-49d5f5",
  "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",
    "architecture": "qwen3_5_moe",
    "source": "mlx-community/Qwen3.6-35B-A3B-4bit",
    "fileSizeBytes": 20402204271,
    "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": 48,
    "osName": "macOS",
    "osVersion": "26.5.2"
  },
  "decodeTpsMean": 83.4,
  "prefillTpsMean": 944.4,
  "ttftP50Ms": 4335.55,
  "idleTpsMean": 19456,
  "peakRssMb": 21504,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.68204,
  "bundleSha256": "ba5fd98a135ecb2004365ec6608690e34acd4b1546d26bf6f994d441f3f2f2cd",
  "createdAt": "2026-07-02T05:33:44.692Z"
}