Sarvam
Indian models focused on 22 languages of India. Sarvam 30B and 105B (2026) are MoE models with strong reasoning and agent skills.
- Developer
- Sarvam AI, India
- First release
- Oct 2024
- Latest release
- Mar 2026
- Sizes
- 2B – 105B-A10B
- License
- Commercial use allowedMain versions Apache 2.0 (Sarvam-M, Sarvam 30B and 105B)
- Russian
- Not supported
- Ready-made builds
- GGUF, AWQ
- Running
- On your own serverAlso runs without a GPU
- Industries
- Customer support, Public sector
What it does
- Multilingual customer support
- Reasoning and calculation tasks
- Agents with tool calling
Where it is used
Hardware requirements
Versions
- Sarvam 30B / 105B
- Sarvam-M 24B
- Sarvam-1 2B
How to run it
I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.
Frequently asked questions
Can Sarvam be used in a commercial project?
Yes. License: Main versions Apache 2.0 (Sarvam-M, Sarvam 30B and 105B). It allows commercial use, but it is still worth having a lawyer review the license before launch.
What hardware does Sarvam need?
At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.
Does Sarvam support Russian?
No. The model card lists its languages and Russian is not among them.
Where can I download Sarvam and what does it cost?
The Sarvam weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.
How I deploy it for clients
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
Multilingual models from Cohere's research arm, covering 23 to 100+ languages. Tiny Aya (2026, 3.3B) runs on a regular PC, but for non-commercial use only.
DetailsTextApertusSwiss AI (ETH Zurich, EPFL, CSCS) · SwitzerlandCommercial use allowedSwitzerland's public open model: weights, data and recipe are open, with more than 1000 languages in training. Version 1.5 understands images.
DetailsTextQwenAlibaba · ChinaCommercial use with conditionsA family of language models with strong Russian language support, from small versions for a laptop to a flagship on par with commercial APIs.
DetailsSource: huggingface.co/sarvamai/sarvam-105b. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


