Qwopus-GLM-18B-Merged benchmark on an M4 · 24 GB

{
  "runId": "run_744cb955-fffe-4b22-b7fd-64246e16560d",
  "bundleId": "llamacpp-qwopus-glm-18b-healed-q4_k_m.gguf-a411e9",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b8680",
    "buildFlags": "metal"
  },
  "model": {
    "displayName": "Qwopus-GLM-18B-Merged",
    "format": "gguf",
    "quant": "q4_k_m",
    "architecture": "qwen35",
    "source": "Jackrong/Qwopus-GLM-18B-Merged-GGUF:Qwopus-GLM-18B-Healed-Q4_K_M.gguf",
    "fileSizeBytes": 9836641632,
    "lab": {
      "name": "Jackrong",
      "slug": "jackrong"
    },
    "quantizedBy": {
      "name": "Jackrong",
      "slug": "jackrong"
    }
  },
  "device": {
    "cpu": "Apple M4",
    "cpuCores": 10,
    "gpu": "Apple M4",
    "gpuCores": 10,
    "gpuCount": 1,
    "ramGb": 24,
    "osName": "macOS",
    "osVersion": "26.3.1"
  },
  "decodeTpsMean": 6.5,
  "prefillTpsMean": 72.1,
  "ttftP50Ms": 59206.58,
  "idleTpsMean": 505,
  "peakRssMb": 1619.7,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.4067796735491071,
  "bundleSha256": "e69db639421d23a4b8010e7e1e119240770f401a7b6b7f1ec6ef61dad37c8eb8",
  "createdAt": "2026-05-09T04:29:06.411Z"
}