Qwen3.6-35B-A3B benchmark on an M4 · 16 GB

{
  "runId": "run_3d9b841c-6948-4e8e-8dc0-2c8f22718d8b",
  "bundleId": "llamacpp-qwen3.6-35b-a3b-ud-iq2_m.gguf-45a0f8",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b8950",
    "buildFlags": "metal"
  },
  "model": {
    "displayName": "Qwen3.6-35B-A3B",
    "format": "gguf",
    "quant": "ud-iq2_m",
    "architecture": "qwen35moe",
    "source": "unsloth/Qwen3.6-35B-A3B-GGUF:Qwen3.6-35B-A3B-UD-IQ2_M.gguf",
    "fileSizeBytes": 11522702304,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "Unsloth",
      "slug": "unsloth"
    }
  },
  "device": {
    "cpu": "Apple M4",
    "cpuCores": 10,
    "gpu": "Apple M4",
    "gpuCores": 10,
    "gpuCount": 1,
    "ramGb": 16,
    "osName": "macOS",
    "osVersion": "26.4.1"
  },
  "decodeTpsMean": 22.7,
  "prefillTpsMean": 252.9,
  "ttftP50Ms": 16219.02,
  "idleTpsMean": 2869.2,
  "peakRssMb": 3000.3,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.5624850469680059,
  "bundleSha256": "06a63a155ca7de4eb6060ed2cb07a28d992b463353025b730d1eecc033fa80c7",
  "createdAt": "2026-04-28T01:08:05.256Z"
}