Qwen3-4B-Instruct-2507 benchmark on an M5 Pro · 48 GB

{
  "runId": "run_6e3a712b-9625-428b-a71c-2fc26e3135c3",
  "bundleId": "mlx-qwen3-4b-instruct-2507-4bit-508796",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.20",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.2",
    "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 M5 Pro",
    "cpuCores": 15,
    "gpu": "Apple M5 Pro",
    "gpuCores": 16,
    "gpuCount": 1,
    "ramGb": 48,
    "osName": "macOS",
    "osVersion": "26.4.1"
  },
  "decodeTpsMean": 82.9,
  "prefillTpsMean": 2359.8,
  "ttftP50Ms": 1782.34,
  "idleTpsMean": 1925,
  "peakRssMb": 6271,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.8786662193080357,
  "bundleSha256": "dc13d89a629eb9d9dd9459dea03775b320c3fe106e42c6cd468ab9dfe4fe5054",
  "createdAt": "2026-04-13T18:15:31.252Z"
}