Llama 3.2 3B Instruct benchmark on an M1 Max · 64 GB

{
  "runId": "run_073bc90e-81ad-4bc4-8912-d0e48490247f",
  "bundleId": "mlx-llama-3.2-3b-instruct-4bit-225b73",
  "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": "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 M1 Max",
    "cpuCores": 10,
    "gpu": "Apple M1 Max",
    "gpuCores": 32,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "15.6.1"
  },
  "decodeTpsMean": 68.4,
  "prefillTpsMean": 652,
  "ttftP50Ms": 6087.94,
  "idleTpsMean": 1409,
  "peakRssMb": 3517,
  "trialsPassed": 30,
  "trialsTotal": 30,
  "runnabilityScore": 0.7948006452287947,
  "bundleSha256": "62fbe86db21c33400920ce77669770babdcbc4977f3f8ec9d58c8654bd60b79a",
  "createdAt": "2026-03-23T01:14:13.731Z"
}