Qwen3-4B-Instruct-2507 benchmark on an M1 Max · 64 GB

{
  "runId": "run_7f79a3b8-3f97-4f76-8b3d-2c17746c852a",
  "bundleId": "mlx-qwen3-4b-instruct-2507-4bit-6b6186",
  "status": "verified",
  "promptTokens": 122880,
  "completionTokens": 30720,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.8",
    "gitSha": "753787f"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.0",
    "buildFlags": null
  },
  "model": {
    "displayName": "Qwen3-4B-Instruct-2507",
    "format": "mlx",
    "quant": "4bit",
    "architecture": "qwen3",
    "source": "mlx-community/Qwen3-4B-Instruct-2507-4bit",
    "fileSizeBytes": 2263022417,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M1 Max",
    "cpuCores": 10,
    "gpu": "Apple M1 Max",
    "gpuCores": 32,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "15.6.1"
  },
  "decodeTpsMean": 39.9,
  "prefillTpsMean": 290.2,
  "ttftP50Ms": 14294.89,
  "idleTpsMean": 3106,
  "peakRssMb": 4176,
  "trialsPassed": 30,
  "trialsTotal": 30,
  "runnabilityScore": 0.6972744605654762,
  "bundleSha256": "ae98d4326dd565c983a2e25eed1ff1620606f34554c5bc3aff02c177ca09d9c9",
  "createdAt": "2026-03-23T03:11:28.562Z"
}