{"slug": "show-hn-boole-1-7b-a-1-bit-llm-that-outperforms-bonsai-1-7b", "title": "Show HN: Boole-1.7B, a 1-bit LLM that outperforms Bonsai-1.7B", "summary": "Precision Numerics released Boole-1.7B, a 1-bit version of Qwen3-1.7B that retains 85.9% of BF16 performance at 247MB, 13.9x smaller than the full-precision model. The company said Boole-1.7B outperforms 1-bit Bonsai-1.7B and similar-sized LFM models and nearly matches 1.58-bit Bonsai-1.7B, targeting low-latency English tasks in non-thinking mode. Weights are published on Hugging Face and a browser chat demo is available, with Precision Numerics saying it will ship more capable open-source models soon.", "body_md": "Introducing Boole-1.7B, a 1-bit version of Qwen3-1.7B.\n\nBoole-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.\n\nIt’s intended for low-latency tasks using English and non-thinking mode. To learn more,\n\n- Blog: [https://precisionnumerics.ai/blog/boole-1p7b](https://precisionnumerics.ai/blog/boole-1p7b)\n\n- Weights: [https://huggingface.co/precision-numerics/Boole-1.7B](https://huggingface.co/precision-numerics/Boole-1.7B)\n\n- Chat in browser: [https://precisionnumerics.ai/chat/](https://precisionnumerics.ai/chat/)\n\nWe're going to ship more capable models soon for the open-source community. Let us know what models/capabilities you want to see next!\n\nComments URL: [https://news.ycombinator.com/item?id=50058167](https://news.ycombinator.com/item?id=50058167)\n\nPoints: 1\n\n# Comments: 1", "url": "https://wpnews.pro/news/show-hn-boole-1-7b-a-1-bit-llm-that-outperforms-bonsai-1-7b", "canonical_source": "https://precisionnumerics.ai/blog/boole-1p7b", "published_at": "2026-10-12 15:49:48+00:00", "updated_at": "2026-10-12 16:19:49.931696+00:00", "lang": "en", "topics": ["large-language-models", "machine-learning", "ai-research", "ai-products"], "entities": ["Precision Numerics", "Boole-1.7B", "Qwen3-1.7B", "Bonsai-1.7B", "Hugging Face", "LFM"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-boole-1-7b-a-1-bit-llm-that-outperforms-bonsai-1-7b", "markdown": "https://wpnews.pro/news/show-hn-boole-1-7b-a-1-bit-llm-that-outperforms-bonsai-1-7b.md", "text": "https://wpnews.pro/news/show-hn-boole-1-7b-a-1-bit-llm-that-outperforms-bonsai-1-7b.txt", "jsonld": "https://wpnews.pro/news/show-hn-boole-1-7b-a-1-bit-llm-that-outperforms-bonsai-1-7b.jsonld"}}