Qwen3.5-4B benchmark on an M4 · 24 GB

{
  "runId": "run_c01e638d-e2f3-4e1a-ad7a-543ff5a7d0d9",
  "bundleId": "llamacpp-qwen3.5-4b-q3_k_m.gguf-19cc26",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "50c24e0"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b9260",
    "buildFlags": "metal"
  },
  "model": {
    "displayName": "Qwen3.5-4B",
    "format": "gguf",
    "quant": "q3_k_m",
    "architecture": "qwen35",
    "source": "unsloth/Qwen3.5-4B-GGUF:Qwen3.5-4B-Q3_K_M.gguf",
    "fileSizeBytes": 2293388448,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "Unsloth",
      "slug": "unsloth"
    }
  },
  "device": {
    "cpu": "Apple M4",
    "cpuCores": 10,
    "gpu": "Apple M4",
    "gpuCores": 10,
    "gpuCount": 1,
    "ramGb": 24,
    "osName": "macOS",
    "osVersion": "26.5"
  },
  "decodeTpsMean": 25.9,
  "prefillTpsMean": 321.1,
  "ttftP50Ms": 12779.67,
  "idleTpsMean": 0,
  "peakRssMb": 1130.4,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.6470207217261905,
  "bundleSha256": "a73d0078b6af84d1b8304d11fbf6f16bee0c91d77229be0a6582d7eaf256b1e2",
  "createdAt": "2026-05-21T12:52:08.640Z"
}