Qwen3-Coder-30B-A3B-Instruct benchmark on an M4 Max · 36 GB

{
  "runId": "run_6107da26-817d-4811-8b9e-505751286ea3",
  "bundleId": "mlx-qwen3-coder-30b-a3b-instruct-mlx-4bit-856d04",
  "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-Coder-30B-A3B-Instruct",
    "format": "mlx",
    "quant": "4bit",
    "architecture": "qwen3_moe",
    "source": "lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-4bit",
    "fileSizeBytes": 17174780668,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "LM Studio",
      "slug": "lmstudio"
    }
  },
  "device": {
    "cpu": "Apple M4 Max",
    "cpuCores": 14,
    "gpu": "Apple M4 Max",
    "gpuCores": 32,
    "gpuCount": 1,
    "ramGb": 36,
    "osName": "macOS",
    "osVersion": "15.7.4"
  },
  "decodeTpsMean": 88.4,
  "prefillTpsMean": 1229.8,
  "ttftP50Ms": 3329.56,
  "idleTpsMean": 17408,
  "peakRssMb": 18432,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.6798042857142857,
  "bundleSha256": "9587dd210582ce9ce9ee8ffa97d91f6b8be04ad63c9ff25e8340c993ef118939",
  "createdAt": "2026-04-07T14:57:44.471Z"
}