BITCOS
AssessTechniques
A bitmap-and-compacted-signs format for storing ternary model weights more efficiently.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by research-stage coverage, with 1 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 7The New Stack·9/17/2026researchIntel Compresses Ternary LLM Weights Below 1.58 Bits with BITCOS
Intel researchers introduced BITCOS, a storage format that compresses ternary model weights by separating zero positions from sign bits, without changing the model’s weights or outputs. In tests across multiple checkpoints and hardware platforms, it reduced storage to as low as 1.485 bits per weight and improved decoding throughput by up to 27%.