https://cognaptus.com/tags/post-training-quantization/ Recent content in Post-Training Quantization on Cognaptus Hugo -- 0.145.0 en-us Tue, 20 Jan 2026 00:00:00 +0000 https://cognaptus.com/blog/2026-01-20-faq-it-till-you-make-it-fixing-llm-quantization-by-teaching-models-their-own-family-history/ Tue, 20 Jan 2026 00:00:00 +0000 https://cognaptus.com/blog/2026-01-20-faq-it-till-you-make-it-fixing-llm-quantization-by-teaching-models-their-own-family-history/ A mechanism-first reading of FAQ, a data-centric post-training quantization method that uses larger in-family models to regenerate calibration data and reduce quantization damage.