4-bit quantization is not applied to all layers, some are kept 8/16-bit. | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

storus 76 days ago | parent | context | favorite | on: Qwen3.6-27B: Flagship-Level Coding in a 27B Dense ...

4-bit quantization is not applied to all layers, some are kept 8/16-bit.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact