Qwen3.5-27B (GLM-5.1 Distill) v1 benchmark on an M5 Pro · 64 GB

{
  "runId": "run_b1daa27e-3b1a-4a22-9aa3-6087e3c4decd",
  "bundleId": "llamacpp-qwen3.5-27b-glm5.1-distill-v1-q2_k.gguf-7dfe5f",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.22",
    "gitSha": "50c24e0"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b8920",
    "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 M5 Pro",
    "cpuCores": 18,
    "gpu": "Apple M5 Pro",
    "gpuCores": 20,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.5.1"
  },
  "decodeTpsMean": 19.7,
  "prefillTpsMean": 282,
  "ttftP50Ms": 14682.48,
  "idleTpsMean": 9158.9,
  "peakRssMb": 9514.7,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.5687454665411087,
  "bundleSha256": "4d2533607551b84990d7a0d9b848e44e2c01e48b798f8553dbd8dd1866e4997e",
  "createdAt": "2026-07-01T00:49:34.918Z"
}