Sarvam 30B
Open weightsOpen weightsText30B parametersReasoning
Sarvam family model by Sarvam.
About the Sarvam family
Sarvam's Indian sovereign models (M, 30B, 105B with effort tiers) optimized for Indic languages and voice, built under the IndiaAI Mission.
All Sarvam modelsHow this one is configured
This configuration runs in reasoning mode (thinks step-by-step before answering); ~30B parameters.
Also runs at: high effort
Effort controls how long the model thinks before answering — higher effort usually means better answers on hard problems, at the cost of speed and money. Same model underneath, so they share this page.