Qwen3.6-35B-A3B benchmark on an M4 Max · 128 GB

{
  "runId": "run_c51c5fe8-f301-4fdd-a9a9-e54a354577a2",
  "bundleId": "llamacpp-qwen3.6-35b-a3b-ud-q4_k_s.gguf-93df5f",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.18",
    "gitSha": "c60e6d1"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b8890",
    "buildFlags": "metal"
  },
  "model": {
    "displayName": "Qwen3.6-35B-A3B",
    "format": "gguf",
    "quant": "ud-q4_k_s",
    "architecture": "qwen35moe",
    "source": "unsloth/Qwen3.6-35B-A3B-GGUF:Qwen3.6-35B-A3B-UD-Q4_K_S.gguf",
    "fileSizeBytes": 20893015008,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "Unsloth",
      "slug": "unsloth"
    }
  },
  "device": {
    "cpu": "Apple M4 Max",
    "cpuCores": 16,
    "gpu": "Apple M4 Max",
    "gpuCores": 40,
    "gpuCount": 1,
    "ramGb": 128,
    "osName": "macOS",
    "osVersion": "26.4.1"
  },
  "decodeTpsMean": 74.1,
  "prefillTpsMean": 1106.9,
  "ttftP50Ms": 3728.89,
  "idleTpsMean": 15886.4,
  "peakRssMb": 17342.8,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.8097885442243303,
  "bundleSha256": "0fd7ea8af164be99b3bd38869d1796d5b8ae7465caa9a9376ebc3b068d419935",
  "createdAt": "2026-04-24T08:06:05.034Z"
}