Model Releases

Sarvam AI open-sources Sarvam 30B and Sarvam 105B reasoning models

Original title:Open-Sourcing Sarvam 30B and 105B

AI summary

Sarvam AI has open-sourced Sarvam 30B and Sarvam 105B, two reasoning models trained from scratch, under the Apache 2.0 license. Both use a MoE architecture, and all training was completed in India on compute provided by the IndiaAI mission.

Key Takeaways

  • Sarvam AI has open-sourced Sarvam 30B and Sarvam 105B,two reasoning models trained from…
  • 0 license.
  • Both use a MoE architecture,and all training was completed in India on compute provided by the…

Quick Facts

Published
Updated
Source
Sarvam AI(网页)
Category
Model Releases
AI score
65
Read the original Read the full article at the original source
Why it matters

原文给出两款从零训练的开源推理模型的架构、训练流程和基准数据,并说明针对印度语言的优化与部署效率,可据此评估其与同类模型的差异。

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: Sarvam AI open-sources Sarvam 30B and Sarvam 105B reasoning models. March 6, 2026. https://new.nat6.net/en/news/cmtym6j8y0006roq1y3q68vd8/

View all →