Granite Switch 4.1.1 — Update models like you update software

蓝旅人AI 前沿📡 Hugging Face Blog2026-10-30496 阅读💛 168 收藏
Back to Articles

Granite Switch 4.1.1 — Update models like you update software

Enterprise Article
Published October 29, 2026
Kate Soule's avatar
Kate Soule
katesoule
IBM Granite's avatar ibm-granite
Luis A Lastras's avatar
Luis A Lastras
GrizleeBer
IBM Granite's avatar ibm-granite
Subhajit Chaudhury's avatar
Subhajit Chaudhury
subhajit1412
IBM Granite's avatar ibm-granite
Abraham Daniels's avatar
Abraham Daniels
abedaniels
IBM Granite's avatar ibm-granite

granite_switch_adapter_swap

Just over a week ago, we released Granite Switch 4.1, showing that our modular Switch architecture lets you configure a language model with specialized, cache-efficient adapters — adding new expertise on a single endpoint.

Granite Switch 4.1.1 is a patch release. The version number means what it means in software: fully backwards compatible with 4.1, no migration, incremental improvements under the hood.

  1. Updated Granite Speech ASR model — multilingual speech-to-text across 10 languages with native punctuation and capitalization, so transcripts are ready for downstream models without a formatting pass.
  2. Updated Decision adapter in granitelib-core — featuring improved overall performance on the Jev Decision Index test set.

While we are excited about these new features, what is notable is the speed and efficiency with which our teams could release this update. Apart from training the new ASR model and Decision adapter, nothing was recomputed: the base model is untouched. You compose the latest adapters you want and deploy.

This pattern can power far more than patch releases to an IBM-provided model. We're working on tutorials and an Adapter SDK so developers and third-party providers can build their own adapters — iterate on versions, test features, and ship updates the way you ship software. More soon.

Until then, test out our latest models, and try out the new multilingual and punctuation capabilities powering our Speech-to-Decisions demo.

文章评论(12)

拾贝者17 天前

很有价值的分享,感谢整理。

回复
星寻梦17 天前

支持作者,持续关注中。

回复
吴超17 天前

实测过类似工具,作者说的基本属实。

回复
星观澜17 天前

很有价值的分享,感谢整理。

回复
墨向阳17 天前

看标题就点进来了,内容果然没让人失望。

回复
曹浩17 天前

赞同,实践出真知。

回复
龙文博17 天前

这个观点很中肯,深有同感。

回复
石佳琪17 天前

这个观点很中肯,深有同感。

回复
蓝临风16 天前

看标题就点进来了,内容果然没让人失望。

回复
墨沐雨16 天前

不错不错,已加入书签。

回复
星观澜16 天前

作者写得真不错,学到了不少。

回复
雪影16 天前

整理得太全面了,省了我不少时间。

回复