Government Of India
A-
A
A+
sarvam-105b
Sarvam-105B is an advanced Mixture-of-Experts (MoE) model with 10.3B active parameters, designed for superior performance across a wide range of complex tasks. It is highly optimized for complex reasoning, with particular strength in agentic tasks, mathematics, and coding.
About Model
Read more about the model - https://www.sarvam.ai/blogs/sovereign-models
sarvam-105b
Metadata
Apache 2.0
sarvamai
Mixture of Experts (MoE) Language Model
Transformers
Open
Sector Agnostic
06/03/26 14:33:37
0
Activity Overview
0
10 
52 
0
Tags
- Transformers
- safetensors
- sarvam_mla
- Text Generation
- conversational
- custom_code
- en
- hi
- bn
- ta
- te
- mr
- gu
- kn
- ml
- pa
- or
- as
- ur
- sa
- ne
- sd
- kok
- mai
- doi
- mni
- sat
- ks
- bo
- license:apache-2.0
- region:us
License Control
Apache 2.0
More Models from Sarvam AI
sarvam-30B
Sarvam-30B is an advanced Mixture-of-Experts (MoE) model with 2.4B non-embedding active parameters, designed primarily for practical deployment. It combines strong reasoning, reliable coding ability, and best-in-class conversational quality across Indian languages. Sarvam-30B is built to run reliably in resource-constrained environments and can handle multilingual voice calls while performing tool calls.
sarvam-105b
Sarvam-105B is an advanced Mixture-of-Experts (MoE) model with 10.3B active parameters, designed for superior performance across a wide range of complex tasks. It is highly optimized for complex reasoning, with particular strength in agentic tasks, mathematics, and coding.
region:us
license:apache-2.0
bo
ks
sat
mni
doi
mai
kok
sd
ne
sa
ur
as
or
pa
ml
kn
gu
mr
te
ta
bn
hi
en
custom_code
conversational
Text Generation
sarvam_mla
Transformers
safetensors
- 0
- 10
- 0
53
Updated 1 day(s) ago
SARVAM AI
sarvamM
Multilingual, hybrid-reasoning, text-only language model built on Mistral-Small
pa
Transformers
safetensors
mistral
Text Generation
conversational
en
bn
hi
kn
gu
mr
ml
or
ta
te
base_model:mistralai/Mistral-Small-3.1-24B-Base-2503
base_model:finetune:mistralai/Mistral-Small-3.1-24B-Base-2503
license:apache-2.0
autotrain_compatible
text-generation-inference
endpoints_compatible
region:us
- 1
- 48
- 0
- 749
Updated 7 month(s) ago
SARVAM AI
sarvamtranslate
Translation model for 22 Indian Languages
kn
en
gu
gom
doi
brx
bn
as
Translation
image-text-to-text
gemma3
ks
hi
Transformers
safetensors
region:us
endpoints_compatible
text-generation-inference
license:gpl-3.0
base_model:finetune:google/gemma-3-4b-it
base_model:google/gemma-3-4b-it
ur
te
ta
sd
sat
sa
pa
or
ne
mr
mni
ml
mai
- 1
- 49
- 0
- 821
Updated 8 month(s) ago
SARVAM AI
sarvam-1
India's first indic model, pretrained on 4 trillion tokens
shuka-v1
Multilingual audio to text model
© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.