LFM2.5-350M benchmark on an M4 Pro · 24 GB

{
  "runId": "run_0abd9812-4f22-48a1-a32b-017a9bf9908c",
  "bundleId": "llamacpp-lfm2.5-350m-q8_0.gguf-2819d0",
  "status": "pending",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "2899067"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b9260",
    "buildFlags": "metal"
  },
  "model": {
    "displayName": "LFM2.5-350M",
    "format": "gguf",
    "quant": "q8_0",
    "architecture": "lfm2",
    "source": "LiquidAI/LFM2.5-350M-GGUF:LFM2.5-350M-Q8_0.gguf",
    "fileSizeBytes": 379217632,
    "lab": {
      "name": "Liquid AI",
      "slug": "liquid"
    },
    "quantizedBy": {
      "name": "Liquid AI",
      "slug": "liquid"
    }
  },
  "device": {
    "cpu": "Apple M4 Pro",
    "cpuCores": 14,
    "gpu": "Apple M4 Pro",
    "gpuCores": 20,
    "gpuCount": 1,
    "ramGb": 24,
    "osName": "macOS",
    "osVersion": "26.5"
  },
  "decodeTpsMean": 370.4,
  "prefillTpsMean": 8613.4,
  "ttftP50Ms": 475.9,
  "idleTpsMean": 282.3,
  "peakRssMb": 515.5,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.9910103934151785,
  "bundleSha256": "7386de496e985095a48bbbe0ab8f71817142fdc47991630d0600f5ed8a74b2f3",
  "createdAt": "2026-05-29T12:15:12.453Z"
}