Qwen3.6-27B benchmark on an M5 Max · 64 GB

{
  "runId": "run_a759e74f-ff07-456d-84f6-a92fe515073c",
  "bundleId": "llamacpp-qwen3.6-27b-q4_k_m.gguf-239423",
  "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": "Qwen3.6-27B",
    "format": "gguf",
    "quant": "q4_k_m",
    "architecture": "qwen35",
    "source": "lmstudio-community/Qwen3.6-27B-GGUF:Qwen3.6-27B-Q4_K_M.gguf",
    "fileSizeBytes": 16547398784,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "LM Studio",
      "slug": "lmstudio"
    }
  },
  "device": {
    "cpu": "Apple M5 Max",
    "cpuCores": 18,
    "gpu": "Apple M5 Max",
    "gpuCores": 40,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.4.1"
  },
  "decodeTpsMean": 25.6,
  "prefillTpsMean": 477.4,
  "ttftP50Ms": 8664.02,
  "idleTpsMean": 8877.2,
  "peakRssMb": 9384.3,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.6300648815336682,
  "bundleSha256": "3df1cb16597ab4965e3c31d45fc21ec4938a0b0c35422571c9179377455a9127",
  "createdAt": "2026-04-24T05:59:02.363Z"
}