Boole-1.7B: A 1-bit Qwen3-1.7B model that outperforms Bonsai-1.7B
英文标题：Boole-1.7B: A 1-bit Qwen3-1.7B model that outperforms Bonsai-1.7B
We're launching Precision Numerics by releasing Boole-1.7B, a 1-bit version of Qwen3-1.7B. 247 MB packed weights: 13.9× smaller than BF16. 85.9% of the BF16 model’s average score across our 10-task evaluation - outperforms 1-bit Bonsai-1.7B and nearly matches 1.58-bit Bonsai-1.7B. Try it loc
打开原文相关 2 · 机会 2
中文
We're launching Precision Numerics by releasing Boole-1.7B, a 1-bit version of Qwen3-1.7B. 247 MB packed weights: 13.9× smaller than BF16. 85.9% of the BF16 model’s average score across our 10-task evaluation - outperforms 1-bit Bonsai-1.7B and nearly matches 1.58-bit Bonsai-1.7B. Try it loc
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
We're launching Precision Numerics by releasing Boole-1.7B, a 1-bit version of Qwen3-1.7B. 247 MB packed weights: 13.9× smaller than BF16. 85.9% of the BF16 model’s average score across our 10-task evaluation - outperforms 1-bit Bonsai-1.7B and nearly matches 1.58-bit Bonsai-1.7B. Try it loc