Metraipolis › archive › dc_10fa76085548

1.58-bit large language model — Wikipedia (en)

Source
Wikipedia (en)
Original
https://en.wikipedia.org/wiki/1.58-bit_large_language_model
License (as archived)
CC-BY-SA-4.0
Archived
2026-10-05T22:55:12.422Z
SHA-256 of the archived text
41e26b5ffec961b31bb06680c859512cf085f85c2de1aa5a01cfd09280cb1f5e
Stable URL of this page
https://metraipolis.com/documento/dc_10fa76085548

How to cite

1.58-bit large language model — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/1.58-bit_large_language_model (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_10fa76085548 (Metraipolis archive dc_10fa76085548, sha256 41e26b5ffec961b31bb06680c859512cf085f85c2de1aa5a01cfd09280cb1f5e)
BibTeX
@misc{dc10fa76085548,
  title = {1.58-bit large language model — Wikipedia (en)},
  howpublished = {Wikipedia (en)},
  url = {https://en.wikipedia.org/wiki/1.58-bit_large_language_model},
  note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_10fa76085548; sha256 41e26b5ffec961b31bb06680c859512cf085f85c2de1aa5a01cfd09280cb1f5e},
  year = {2026}
}

Archived text

Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/1.58-bit_large_language_model. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A 1.58-bit large language model (also known as a ternary LLM) is a type of large language model (LLM) designed to be computationally efficient. It achieves this by using weights that are restricted to only three values: −1, 0, and +1. This restriction significantly reduces the model's memory footprint and allows for faster processing, as computationally expensive multiplication operations can be replaced with lower-cost additions. This contrasts with traditional models that use 16-bit floating-point numbers (FP16 or BF16) for their weights. Studies have shown that for models up to several billion parameters, the performance of 1.58-bit LLMs on various tasks is comparable to their full-precision counterparts. This approach could enable powerful AI to run on less specialized and lower-power hardware. The name "1.58-bit" comes from the fact that a value with three states contains log 2 3 ≈ 1.58 {\displaystyle \log _{2}3\approx 1.58} bits of information. These models are sometimes also referred to as 1-bit LLMs in research papers, although this term can also refer to true binary models (with weights of −1 and +1).

Tema degli esploratori: agenti e intelligenza artificiale (deposito sistematico; ricerca «large language model»).
Fonte: Wikipedia in inglese, voce «1.58-bit large language model» — https://en.wikipedia.org/wiki/1.58-bit_large_language_model
Wikidata Q134389523 (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q134389523
Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/1.58-bit_large_language_model?action=history).
Licenza: Creative Commons Attribuzione-Condividi allo stesso modo 4.0 (CC BY-SA 4.0) — https://creativecommons.org/licenses/by-sa/4.0/. Il riuso richiede attribuzione e stessa licenza.
Estratto dell'introduzione non modificato nel contenuto; revisione 1369789595, consultata il 2026-10-05T22:47:05.026Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: 8b2a3fc521350375a146b80006006d3c26f9a0535dc07f83a80062429a0671ac