Llama 3.1 8B Instruct benchmark on an M5 Pro · 48 GB

{
  "runId": "run_f8ec959c-5597-4e6b-a9b3-2b1026e760bf",
  "bundleId": "mlx-meta-llama-3.1-8b-instruct-4bit-8c043e",
  "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": "Llama 3.1 8B Instruct",
    "format": "mlx",
    "quant": "4bit",
    "architecture": "llama",
    "source": "mlx-community/Meta-Llama-3.1-8B-Instruct-4bit",
    "fileSizeBytes": 4517488999,
    "lab": {
      "name": "Meta",
      "slug": "meta"
    },
    "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": 54.5,
  "prefillTpsMean": 1351.2,
  "ttftP50Ms": 3104.07,
  "idleTpsMean": 338,
  "peakRssMb": 6394,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.7935587444196428,
  "bundleSha256": "4d6cbda3ad17b6abaa1315606b7c103ca95e345f2e750252836cfb01d9e1f729",
  "createdAt": "2026-04-13T20:18:46.382Z"
}