30B / 2.4B active (MoE), 105B / 10.3B active (MoE)
Apache 2.0
Joint open-source release of two MoE reasoning models: Sarvam-30B and Sarvam-105B; both are positioned for multilingual and Indian-language performance with strong coding/reasoning capability. Sarvam-30B uses an efficiency-oriented 19-layer MoE design with top-6 routing over 128 experts, while Sarvam-105B scales to higher capability with top-8 routing over 128 experts, MLA-style attention, and 128K context support via YaRN-style scaling.