Sarvam 30B
Sarvam 30B is an Indian multilingual language model trained from scratch for practical local deployment. Its sparse experts support coding, reasoning, tool use, and conversational quality across 22 Indian languages. The 30B tier uses fewer layers and grouped key-value attention to reduce inference overhead. Public weights were released on March 6, following the family’s February announcement. The checkpoint supports up to 128K context, while reported evaluations use shorter task-specific limits. Model outputs require task-specific checks in languages and domains beyond the training focus.
2026-03-06
30B total, 2.4B non-embedding active
Mixture-of-Experts Transformer
Apache-2.0
Specifications
- Parameters
- 30B total, 2.4B non-embedding active
- Architecture
- Mixture-of-Experts Transformer
- License
- Apache-2.0
- Context Window
- 131,072 tokens
- Type
- text
- Modalities
- text
Benchmark Scores
Advanced Specifications
- Model Family
- Sarvam
- API Access
- Not Available
- Chat Interface
- Not Available
- Multilingual Support
- Yes
Capabilities & Limitations
- Capabilities
- multilingual generationreasoningcodingtool use
- Known Limitations
- Language performance varies by taskSparse activation does not remove total weight memory needsOriginal 30B hosted API was deprecated in August 2026
- Notable Use Cases
- Indian-language assistantsprivate multilingual inferencecoding and agent research