Qwopus3.5-27B-v3 benchmark on an M4 Max · 36 GB

{
  "runId": "run_c7ba02ee-f4da-49bd-a346-bce6bd9e6a19",
  "bundleId": "llamacpp-qwopus3.5-27b-v3-q6_k.gguf-237396",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.20",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b8680",
    "buildFlags": "metal"
  },
  "model": {
    "displayName": "Qwopus3.5-27B-v3",
    "format": "gguf",
    "quant": "q6_k",
    "architecture": "qwen35",
    "source": "Jackrong/Qwopus3.5-27B-v3-GGUF:Qwopus3.5-27B-v3-Q6_K.gguf",
    "fileSizeBytes": 22082525056,
    "lab": {
      "name": "Jackrong",
      "slug": "jackrong"
    },
    "quantizedBy": {
      "name": "Jackrong",
      "slug": "jackrong"
    }
  },
  "device": {
    "cpu": "Apple M4 Max",
    "cpuCores": 14,
    "gpu": "Apple M4 Max",
    "gpuCores": 32,
    "gpuCount": 1,
    "ramGb": 36,
    "osName": "macOS",
    "osVersion": "15.6.1"
  },
  "decodeTpsMean": 14,
  "prefillTpsMean": 189.4,
  "ttftP50Ms": 21632.01,
  "idleTpsMean": 21844.3,
  "peakRssMb": 22729,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.2991084635416667,
  "bundleSha256": "bc9d743595288efa65ec5d986404b41e831c4786c793083be2dd1a9a5a92d097",
  "createdAt": "2026-04-11T07:12:40.147Z"
}