Other

Gemma 4 released: the strongest open-source models at every size

Original title:Excited to launch Gemma 4: the best open models in the world for their respective sizes. Available i...

AI summary

The open-source Gemma 4 models are released in four sizes: a 31B dense version for maximum performance, a 26B MoE version for low latency, and 2B and 4B versions for edge devices, all fine-tunable for specific tasks.

Key Takeaways

  • The open-source Gemma 4 models are released in four sizes: a 31B dense version for maximum…
  • a 26B MoE version for low latency
  • and 2B and 4B versions for edge devices,all fine-tunable for specific tasks.

Quick Facts

Published
Updated
Source
X:Demis Hassabis (@demishassabis)
Category
Other
Read the original Read the full article at the original source
Why it matters

Google 发布 Gemma 4 开源模型,覆盖 2B 至 31B 多尺寸,支持端侧与 MoE 架构

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Gemma 4 released: the strongest open-source models at every size. April 3, 2026. https://new.nat6.net/en/news/cmnw1yqoh00toslc3u4hk2dqn/

View all →