Qwen3.5-27B (GLM-5.1 Distill) v1 benchmark on an M4 · 24 GB

{
  "runId": "run_6c06ad43-472d-4cf9-9952-129c91d638fb",
  "bundleId": "llamacpp-qwen3.5-27b-glm5.1-distill-v1-q2_k.gguf-fc8271",
  "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": "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": "Apple M4",
    "cpuCores": 10,
    "gpu": "Apple M4",
    "gpuCores": 10,
    "gpuCount": 1,
    "ramGb": 24,
    "osName": "macOS",
    "osVersion": "26.3.1"
  },
  "decodeTpsMean": 4.4,
  "prefillTpsMean": 37.8,
  "ttftP50Ms": 107872.08,
  "idleTpsMean": 4605.6,
  "peakRssMb": 5559.6,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.29169827008928567,
  "bundleSha256": "332400646797ede11ffe58ad7d4ecad348443b57f860d05643398c09557a2584",
  "createdAt": "2026-05-09T07:02:33.969Z"
}