Qwen3.5-35B-A3B benchmark on an M4 Max · 36 GB

{
  "runId": "run_cefc84c9-5951-4624-8714-4e659c8383c1",
  "bundleId": "mlx-qwen3.5-35b-a3b-4bit-327500",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.19",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.1",
    "buildFlags": null
  },
  "model": {
    "displayName": "Qwen3.5-35B-A3B",
    "format": "mlx",
    "quant": "4bit",
    "architecture": "qwen3_5_moe",
    "source": "mlx-community/Qwen3.5-35B-A3B-4bit",
    "fileSizeBytes": 20391679439,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M4 Max",
    "cpuCores": 14,
    "gpu": "Apple M4 Max",
    "gpuCores": 32,
    "gpuCount": 1,
    "ramGb": 36,
    "osName": "macOS",
    "osVersion": "15.7.4"
  },
  "decodeTpsMean": 105.1,
  "prefillTpsMean": 1412.7,
  "ttftP50Ms": 2945.26,
  "idleTpsMean": 19456,
  "peakRssMb": 21504,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.6706350000000001,
  "bundleSha256": "81020cfeb5b3422f8cc6836fe5ae03bf04090b59c40b8c13b1b84468146a0ec1",
  "createdAt": "2026-04-07T10:52:07.797Z"
}