Breaking the 1.58-bit Barrier for Ternary LLMs
This story is from 2026-09-16. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.16338v1 Announce Type: new 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…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-09-16 04:00 · arXiv cs.AI
Breaking the 1.58-bit Barrier for Ternary LLMs