{
  "id": 1000944,
  "title": "Benchmark Averages Hide the Failures That Matter: Quantizing ESM-2 for Protein Variant-Effect Prediction",
  "url": "https://urgent.news/2026/08/15/benchmark-averages-hide-the-failures-that-matter-quantizing-esm-2-for",
  "topic": "science",
  "section": "Science",
  "published": "2026-08-15T00:00:00.000Z",
  "source": {
    "name": "bioRxiv",
    "slug": "biorxiv",
    "url": "https://www.biorxiv.org/content/10.64898/2026.08.10.744024v1?rss=1"
  },
  "original_language": "en",
  "account": null,
  "summary": "We benchmark six numerical precision configurations for ESM-2 protein language models across throughput, memory footprint and predictive accuracy, on two workloads with sharply different characteristics: bulk embedding extraction and deep mutational scanning (DMS) variant-effect scoring. Accuracy is evaluated on the complete ProteinGym substitution benchmark -- 201 assays, 2.41M variants -- at…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}