Qwen3.5-9B benchmark on an M4 Pro · 24 GB

{
  "runId": "run_5577662a-ab4a-46ee-9876-40b8c01c0152",
  "bundleId": "llamacpp-qwen3.5-9b-q6_k.gguf-3b3db7",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "0.3.0",
    "buildFlags": null
  },
  "model": {
    "displayName": "Qwen3.5-9B",
    "format": "gguf",
    "quant": "q6_k",
    "architecture": "qwen35",
    "source": "unsloth/Qwen3.5-9B-GGUF:Qwen3.5-9B-Q6_K.gguf",
    "fileSizeBytes": 7458301152,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "Unsloth",
      "slug": "unsloth"
    }
  },
  "device": {
    "cpu": "Apple M4 Pro",
    "cpuCores": 12,
    "gpu": "Apple M4 Pro",
    "gpuCores": 16,
    "gpuCount": 1,
    "ramGb": 24,
    "osName": "macOS",
    "osVersion": "15.7.2"
  },
  "decodeTpsMean": 29.3,
  "prefillTpsMean": 332.1,
  "ttftP50Ms": 12356.37,
  "idleTpsMean": 4417.1,
  "peakRssMb": 5029.5,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.5961591471354166,
  "bundleSha256": "602bad0ca43b39746db84293d05e3ecd462c8508eb7c98941a48ec401bee29ab",
  "createdAt": "2026-09-01T12:06:50.636Z"
}