{
  "id": "quantization",
  "code": "PTL-0230",
  "term": "Quantization",
  "aliases": [
    "model quantization",
    "post-training quantization",
    "PTQ",
    "weight quantization",
    "GPTQ",
    "LLM.int8()"
  ],
  "category": "optimization",
  "definition": "Quantization reduces the numeric precision of a model's weights, and sometimes its activations, from 16- or 32-bit floating point to lower-precision formats such as 8-bit or 4-bit integers, cutting memory use and inference cost at some cost in accuracy.",
  "description": "Post-training quantization is applied to a model that has already been trained, without retraining it. LLM.int8() made 8-bit inference practical for large models by keeping a small number of outlier feature dimensions in higher precision. GPTQ quantizes weights to 3 or 4 bits in a single pass, using approximate second-order information to keep accuracy loss small. Quantization is widely used to fit large open-weight models onto fewer GPUs or consumer hardware. Quantization-aware training, which simulates low precision during training, is an alternative to post-training methods. Quantization is often combined with other efficiency methods such as low-rank adaptation and knowledge distillation.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "knowledge-distillation",
    "low-rank-adaptation",
    "kv-cache",
    "speculative-decoding"
  ],
  "introduced": 2022,
  "added": "2026-10-27",
  "sources": [
    {
      "title": "LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale",
      "authors": "Dettmers et al.",
      "year": 2022,
      "url": "https://arxiv.org/abs/2208.07339"
    },
    {
      "title": "GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers",
      "authors": "Frantar et al.",
      "year": 2022,
      "url": "https://arxiv.org/abs/2210.17323"
    }
  ],
  "url": "https://protologue.com/t/quantization/",
  "citation": "Protologue. (2026). Quantization. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0230). https://protologue.com/t/quantization/"
}