Sarvam AI logo

Sarvam 30B

Sarvam AIOpen WeightsPending Human Review

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

Related Models