Qwopus-GLM-18B-Merged benchmark on a GeForce RTX 5070 Ti

{
  "runId": "run_e9869fdd-a799-4897-aa3e-b38590c8bf58",
  "bundleId": "llamacpp-qwopus-glm-18b-healed-q4_k_m.gguf-d03d1f",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b8849",
    "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": "Intel(R) Core(TM) Ultra 7 265KF",
    "cpuCores": 20,
    "gpu": "NVIDIA GeForce RTX 5070 Ti",
    "gpuCores": 0,
    "gpuCount": 1,
    "ramGb": 23,
    "osName": "Fedora Remix for WSL",
    "osVersion": "Unknown"
  },
  "decodeTpsMean": 57.6,
  "prefillTpsMean": 2548.6,
  "ttftP50Ms": 1599.91,
  "idleTpsMean": 1178.6,
  "peakRssMb": 9740.2,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.7228743652950311,
  "bundleSha256": "7bea35ab84e24cb87108deb964692f8e08fdfe002ee6941a2996db495474e4a3",
  "createdAt": "2026-04-19T17:39:25.425Z"
}