Qwen3.6-35B-A3B benchmark on an M4 Max · 128 GB

{
  "runId": "run_5ad5b040-9399-42bd-8ef2-3d639b7d75a3",
  "bundleId": "mlx-qwen3.6-35b-a3b-4bit-34944b",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.18",
    "gitSha": "c60e6d1"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.2",
    "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 Max",
    "cpuCores": 16,
    "gpu": "Apple M4 Max",
    "gpuCores": 40,
    "gpuCount": 1,
    "ramGb": 128,
    "osName": "macOS",
    "osVersion": "26.4.1"
  },
  "decodeTpsMean": 113,
  "prefillTpsMean": 1616.7,
  "ttftP50Ms": 2542.46,
  "idleTpsMean": 19456,
  "peakRssMb": 21504,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.8605225000000001,
  "bundleSha256": "38044bdc8d64f0170e40d19f822965ac1ce2aedcb4437918c20b7f1c6667038d",
  "createdAt": "2026-04-24T08:18:14.698Z"
}