Show HN: Boole-1.7B, a 1-bit LLM that outperforms Bonsai-1.7B
By d7chong · 2026-10-12 · 1 points · 1 comments
https://precisionnumerics.ai/blog/boole-1p7b
Introducing Boole-1.7B, a 1-bit version of Qwen3-1.7B. Boole-1.7B retains 85.9% of BF16 performance using 247MB (13.9x smaller). It outperforms 1-bit Bonsai-1.7B and similar-sized LFM models, and nearly matches 1.58-bit Bonsai-1.7B. It’s intended for low-latency tasks using Engl…
Open the full discussion on BetterNews