Llama 3.2 3B Instruct benchmark on an M5 · 16 GB

{
  "runId": "run_40b96501-acf1-4501-8542-cbe28131a6e1",
  "bundleId": "mlx-llama-3.2-3b-instruct-4bit-8ac326",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "50c24e0"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.3",
    "buildFlags": null
  },
  "model": {
    "displayName": "Llama 3.2 3B Instruct",
    "format": "mlx",
    "quant": "4bit",
    "architecture": "llama",
    "source": "mlx-community/Llama-3.2-3B-Instruct-4bit",
    "fileSizeBytes": 1807496278,
    "lab": {
      "name": "Meta",
      "slug": "meta"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M5",
    "cpuCores": 10,
    "gpu": "Apple M5",
    "gpuCores": 10,
    "gpuCount": 1,
    "ramGb": 16,
    "osName": "macOS",
    "osVersion": "26.5"
  },
  "decodeTpsMean": 46.5,
  "prefillTpsMean": 1957.2,
  "ttftP50Ms": 2042.43,
  "idleTpsMean": 1505,
  "peakRssMb": 3560,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.7744877901785715,
  "bundleSha256": "775f6e3c9536b5b5dd7b8857c9b0dd1685470549786965a4515ae4f74d3d2c96",
  "createdAt": "2026-05-22T04:21:29.660Z"
}