{"data":{"slug":"quantization","etype":"concept","name":"Quantization","cat":"Training & Inference","subtitle":"Fewer bits per weight: how models shrink to fit real hardware.","summary":"Quantization stores weights and activations in fewer bits — 8, 4, even fewer — trading a sliver of accuracy for big memory and speed gains. It is why a 70B model runs on a laptop (GGUF 4-bit), and why hardware generations chase ever-lower precisions: Hopper's FP8 and Blackwell's FP4 are quantization cast in silicon.","attrs":null,"kf":null,"aliases":["FP8","FP4","INT8","4-bit"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":null,"region":null,"asof":"2026-01-15","sources":[{"url":"https://arxiv.org/abs/2210.17323","label":"GPTQ paper"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T02:56:41+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}