Qwen2.5-Coder-7B-Instruct benchmark on an M4 Pro · 48 GB

{
  "runId": "run_87f7f195-8bc5-4586-b1db-f8905671ddae",
  "bundleId": "mlx-qwen2.5-coder-7b-instruct-4bit-eb297c",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.3",
    "buildFlags": null
  },
  "model": {
    "displayName": "Qwen2.5-Coder-7B-Instruct",
    "format": "mlx",
    "quant": "4bit",
    "architecture": "qwen2",
    "source": "mlx-community/Qwen2.5-Coder-7B-Instruct-4bit",
    "fileSizeBytes": 4284346255,
    "lab": {
      "name": "MLX Community",
      "slug": "mlx-community"
    },
    "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": "26.5.2"
  },
  "decodeTpsMean": 48.2,
  "prefillTpsMean": 487.9,
  "ttftP50Ms": 8321.21,
  "idleTpsMean": 2577,
  "peakRssMb": 8159,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.6991424990699405,
  "bundleSha256": "1145d6701a725bd62d968e5b11064e60ace52e5560acddba525c2de1a1ecfa91",
  "createdAt": "2026-07-03T04:19:11.063Z"
}