Qwen3.5-35B-A3B benchmark on an M4 Pro · 48 GB

{
  "runId": "run_bb34b13a-1913-4446-a15c-00fa339ffc09",
  "bundleId": "mlx-qwen3.5-35b-a3b-4bit-78a765",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.20",
    "gitSha": "8b7ba0e481"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.2",
    "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 Pro",
    "cpuCores": 14,
    "gpu": "Apple M4 Pro",
    "gpuCores": 20,
    "gpuCount": 1,
    "ramGb": 48,
    "osName": "macOS",
    "osVersion": "26.4"
  },
  "decodeTpsMean": 72.8,
  "prefillTpsMean": 820.6,
  "ttftP50Ms": 5104.55,
  "idleTpsMean": 19456,
  "peakRssMb": 21504,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.65376,
  "bundleSha256": "8199ef8a48d61bf0a6db8626983a560edb1886a525f838c12879a72a77887623",
  "createdAt": "2026-04-12T15:41:16.476Z"
}