wcir-model benchmark on an AMD's logo.EPYC

<- Runs

Prompt tokens

40,960

Generation tokens

10,240

Trials passed

10/10

Rejected

200.0 tok/s

1,000.0 tok/s

Peak memory

0.00/4 GB

Runs great

Trials

Decode / Prefill Speeds

Metadata

metadata.json
{
  "runId": "run_695feb73-1e8a-452e-8a34-93cf740a58da",
  "bundleId": "mlx-wcir-model-39e3a7",
  "status": "rejected",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.12",
    "gitSha": "3b3f89c"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.30.1",
    "buildFlags": null
  },
  "model": {
    "displayName": "wcir-model",
    "format": "mlx",
    "quant": null,
    "architecture": "qwen3",
    "source": null,
    "fileSizeBytes": null,
    "lab": null,
    "quantizedBy": null
  },
  "device": {
    "cpu": "AMD EPYC",
    "cpuCores": 2,
    "gpu": "None",
    "gpuCores": 0,
    "gpuCount": 0,
    "ramGb": 4,
    "osName": "Ubuntu 22.04 LTS",
    "osVersion": "22.04"
  },
  "decodeTpsMean": 200,
  "prefillTpsMean": 1000,
  "ttftP50Ms": 4096,
  "idleTpsMean": 0,
  "peakRssMb": 0,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.86,
  "bundleSha256": "100830b10677ba7a6a03b776e276403727c3efaef5a3a95f36f25e6318c131d5",
  "createdAt": "2026-09-03T20:20:09.600Z"
}