{"type": "article", "title": "Intel squeezed a 1.58-bit LLM down to 1.485 bits without changing a single weight", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/intel-squeezed-a-1-58-bit-llm-down-to-1-485-bits-without-changing-a-single", "original_source": "https://thenewstack.io/intel-bitcos-ternary-compression/", "published": "2026-09-17T20:51:57+00:00", "accessed": "2026-09-17", "id": "intel-squeezed-a-1-58-bit-llm-down-to-1-485-bits-without-changing-a-single"}