gpt-oss-20b benchmark on an M4 · 32 GB

{
  "runId": "run_201fa900-7c27-44df-a7d1-6e4ebec070fc",
  "bundleId": "mlx-gpt-oss-20b-mxfp4-q8-bf412a",
  "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": "gpt-oss-20b",
    "format": "mlx",
    "quant": "mxfp4",
    "architecture": "gpt_oss",
    "source": "mlx-community/gpt-oss-20b-MXFP4-Q8",
    "fileSizeBytes": 12076207568,
    "lab": {
      "name": "OpenAI",
      "slug": "openai"
    },
    "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": 25,
  "prefillTpsMean": 249.9,
  "ttftP50Ms": 17080.97,
  "idleTpsMean": 1374,
  "peakRssMb": 12288,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.490102380952381,
  "bundleSha256": "b801e0e04fefcc2161c1a05a52acee63a654d97e43f70d6a14ec4a1886df76fe",
  "createdAt": "2026-04-17T17:42:36.700Z"
}