Qwen3.5-27B (GLM-5.1 Distill) v1 benchmark on a GeForce RTX 5070 Ti

{
  "runId": "run_26199d2e-19b4-47a5-aba3-fc8f680ef1eb",
  "bundleId": "llamacpp-qwen3.5-27b-glm5.1-distill-v1-q2_k.gguf-b50732",
  "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": "Qwen3.5-27B (GLM-5.1 Distill) v1",
    "format": "gguf",
    "quant": "q2_k",
    "architecture": "qwen35",
    "source": "Jackrong/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF:Qwen3.5-27B-GLM5.1-Distill-v1-Q2_K.gguf",
    "fileSizeBytes": 10711661344,
    "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": 48.6,
  "prefillTpsMean": 1241.6,
  "ttftP50Ms": 3269.76,
  "idleTpsMean": 1036,
  "peakRssMb": 10574.4,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.6425595807453416,
  "bundleSha256": "b6826918509185f5bb0c0c314b4c73cfff75c4d14ce6a9ded47b8c28acadfa5b",
  "createdAt": "2026-04-19T17:45:39.344Z"
}