Qwen3-Coder-Next benchmark on an M5 Pro · 64 GB

{
  "runId": "run_86c072a7-73d3-4994-adcb-9bc1d22d47f3",
  "bundleId": "mlx-qwen3-coder-next-4bit-8c6f3f",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.22",
    "gitSha": "ff1d570"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.3",
    "buildFlags": null
  },
  "model": {
    "displayName": "Qwen3-Coder-Next",
    "format": "mlx",
    "quant": "4bit",
    "architecture": "qwen3_next",
    "source": "mlx-community/Qwen3-Coder-Next-4bit",
    "fileSizeBytes": 44844286500,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M5 Pro",
    "cpuCores": 18,
    "gpu": "Apple M5 Pro",
    "gpuCores": 20,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.5.1"
  },
  "decodeTpsMean": 72.3,
  "prefillTpsMean": 1622.3,
  "ttftP50Ms": 2575.61,
  "idleTpsMean": 220,
  "peakRssMb": 46080,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.589565,
  "bundleSha256": "657e178f88bb7894a689da5f4ff9796b85d966e93bf24f8ff5e1127c51310826",
  "createdAt": "2026-06-05T22:07:37.399Z"
}