Gemopus 4 26B A4B IT benchmark on an M4 Pro · 64 GB

{
  "runId": "run_fd1db481-4a35-4370-aad4-1c8df80ac6a4",
  "bundleId": "llamacpp-gemopus-4-26b-a4b-it-preview-q4_k_m.gguf-8f887a",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.18",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b8743",
    "buildFlags": "metal"
  },
  "model": {
    "displayName": "Gemopus 4 26B A4B IT",
    "format": "gguf",
    "quant": "q4_k_m",
    "architecture": "gemma4",
    "source": "Jackrong/Gemopus-4-26B-A4B-it-GGUF:Gemopus-4-26B-A4B-it-Preview-Q4_K_M.gguf",
    "fileSizeBytes": 16796011104,
    "lab": {
      "name": "Jackrong",
      "slug": "jackrong"
    },
    "quantizedBy": {
      "name": "Jackrong",
      "slug": "jackrong"
    }
  },
  "device": {
    "cpu": "Apple M4 Pro",
    "cpuCores": 14,
    "gpu": "Apple M4 Pro",
    "gpuCores": 20,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.3"
  },
  "decodeTpsMean": 57.6,
  "prefillTpsMean": 678.3,
  "ttftP50Ms": 6044.2,
  "idleTpsMean": 0.2,
  "peakRssMb": 17537,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.689547121233259,
  "bundleSha256": "d363940c3e48e59a24faec086b56427ca90c5b6783e066bf103de901cd173dbc",
  "createdAt": "2026-04-10T09:24:35.246Z"
}