{
  "@context": "https://schema.org",
  "@type": "TechArticle",
  "@id": "https://anchorfact.org/kb/model-compression",
  "headline": "Model Compression: Pruning, Quantization, and Distillation",
  "description": "Model compression reduces inference cost for deployment on resource-constrained devices. The three pillars — pruning, quantization, and distillation — can be combined for 10x+ compression with minimal accuracy loss.",
  "dateCreated": "2026-05-24T02:49:13.636Z",
  "dateModified": "2026-05-24",
  "author": {
    "@type": "Organization",
    "name": "AnchorFact"
  },
  "publisher": {
    "@type": "Organization",
    "name": "AnchorFact",
    "url": "https://anchorfact.org"
  },
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "anchorfact:confidence": "high",
  "anchorfact:generationMethod": "ai_assisted",
  "citation": [
    {
      "@type": "CreativeWork",
      "name": "A White Paper on Neural Network Quantization",
      "sameAs": "https://arxiv.org/abs/2106.08295"
    },
    {
      "@type": "CreativeWork",
      "name": "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks",
      "sameAs": "https://arxiv.org/abs/1803.03635"
    }
  ]
}