Llama 3.1 8B Instruct benchmark on an M4 · 32 GB

{
  "runId": "run_a995732b-b0c2-4953-b519-e26dd73ed9ae",
  "bundleId": "mlx-meta-llama-3.1-8b-instruct-4bit-dbdf64",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "f68adca"
  },
  "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 M4",
    "cpuCores": 10,
    "gpu": "Apple M4",
    "gpuCores": 10,
    "gpuCount": 1,
    "ramGb": 32,
    "osName": "macOS",
    "osVersion": "15.7.4"
  },
  "decodeTpsMean": 16.1,
  "prefillTpsMean": 141.7,
  "ttftP50Ms": 30001.61,
  "idleTpsMean": 5237,
  "peakRssMb": 6082,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.4907787527901786,
  "bundleSha256": "8321020a57cff2a165a3b481b1fb93f8ba8e80c9a9ae3f6ee2def42dcdd6b7cc",
  "createdAt": "2026-04-17T14:02:39.569Z"
}