gpt-oss-120b benchmark on an M4 Max · 128 GB

{
  "runId": "run_0fd56fa6-a301-4839-9884-509962f97646",
  "bundleId": "mlx-gpt-oss-120b-4bit-6e0418",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.18",
    "gitSha": "c60e6d1"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.2",
    "buildFlags": null
  },
  "model": {
    "displayName": "gpt-oss-120b",
    "format": "mlx",
    "quant": "4bit",
    "architecture": "gpt_oss",
    "source": "mlx-community/gpt-oss-120b-4bit",
    "fileSizeBytes": 65774504710,
    "lab": {
      "name": "OpenAI",
      "slug": "openai"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M4 Max",
    "cpuCores": 16,
    "gpu": "Apple M4 Max",
    "gpuCores": 40,
    "gpuCount": 1,
    "ramGb": 128,
    "osName": "macOS",
    "osVersion": "26.4.1"
  },
  "decodeTpsMean": 84,
  "prefillTpsMean": 820.2,
  "ttftP50Ms": 5001.07,
  "idleTpsMean": 6648,
  "peakRssMb": 66560,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.6403860714285715,
  "bundleSha256": "4c7e485a338a81c857bcfa5d92d3748ea2ebbfbfb31d0e22384160d186a83422",
  "createdAt": "2026-04-24T19:49:26.276Z"
}