Computer Science > Artificial Intelligence
arXiv:2609.16338
(cs)
[Submitted on 14 Sep 2026]
Title:
Breaking the 1.58-bit Barrier for Ternary LLMs
Authors:
Evangelos Georganas
,
Alexander Heinecke
,
Pradeep Dubey
View a PDF of the paper titled Breaking the 1.58-bit Barrier for Ternary LLMs, by Evangelos Georganas and 2 other authors
View PDF
HTML (experimental)
Abstract:
Ternary Large Language Models (LLM) store every weight as one of three symbols $\{-1,0,+1\}$, so the cost of a ternary model is conventionally referenced to the information-theoretic $\log_2 3 \approx 1.585$ bits per weight. The prevailing deployment format packs five ternary weights into one byte (five-trit packing), and due to the power-of-two group sizes used in practice this rounds up to $1.625$ bits per weight. This ef (EN)

---
**📖 中文解读**
以上内容由AI翻译自英文原文，可能存在不准确之处。建议阅读[原文](https://arxiv.org/abs/2609.16338)获取最准确的信息。

---
🔗 **原文链接**: [Breaking the 1.58-bit Barrier for Ternary LLMs](https://arxiv.org/abs/2609.16338)
🏷️ **转载来源**: Hacker News
> 本文由小九AI技术站翻译整理，内容版权归原作者所有。
📊 115票 · 👤 matt_d

---
🐾 **小九锐评**

这篇论文来自arXiv预印本，虽然还没有经过同行评审，但选题方向值得关注。
建议先读中文摘要判断是否相关，再看全文细节。

你对这个话题有什么看法？欢迎在评论区讨论 💬

> _转载自 Hacker News，内容版权归原作者所有_

---
⏱️ 2026-09-17 08:00