Indian Flag
Government Of India
A-
A
A+
Home/Models/sarvam-1

sarvam-1

India's first indic model, pretrained on 4 trillion tokens

About Model

Sarvam-1 is a 2-billion parameter language model designed for Indian languages, optimized for token efficiency and high-quality training data. It outperforms larger models in several benchmarks, providing superior performance on Indic language tasks with enhanced computational efficiency. Built with a custom tokenizer and 4 trillion tokens from diverse sources, Sarvam-1 is ideal for applications like translation and edge device deployment.

sarvam-1

Metadata Metadata

Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)

sarvamai

Multilingual Language Model

Transformers

Open

Sarvam AI

Science, Technology and Research

24/02/25 07:45:49

Aashay Sachdeva

0

Activity Overview Activity Overview

  • Downloads3
  • Redirect 251
  • File Size 0
  • Views 4,814

Tags Tags

    No Tags Found!!

License Control License Control

Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)

More Models from Sarvam AI 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.
MoE Model
  • See Upvoters4
  • Downloads136
  • File Size59.92 GB
  • Views2,092
Updated 2 month(s) ago
SARVAM AI
View Details
share
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.
license:apache-2.0
Transformers
sd
safetensors
Text Generation
conversational
gu
ta
en
or
bn
te
pa
hi
mr
ml
kn
custom_code
as
doi
mni
ne
ur
sat
mai
ks
sa
region:us
sarvam_mla
bo
kok
  • See Upvoters8
  • Downloads444
  • File Size0
  • Views7,271
Updated 2 month(s) ago
SARVAM AI
View Details
share
sarvamM
Multilingual, hybrid-reasoning, text-only language model built on Mistral-Small
region:us
Transformers
safetensors
endpoints_compatible
Text Generation
text-generation-inference
conversational
gu
ta
en
or
bn
te
pa
hi
mr
ml
kn
autotrain_compatible
base_model:finetune:mistralai/Mistral-Small-3.1-24B-Base-2503
base_model:mistralai/Mistral-Small-3.1-24B-Base-2503
mistral
license:apache-2.0
  • See Upvoters1
  • Downloads63
  • File Size0
  • Views1,089
Updated 10 month(s) ago
SARVAM AI
View Details
share
sarvamtranslate
Translation model for 22 Indian Languages
base_model:finetune:google/gemma-3-4b-it
brx
region:us
Transformers
Translation
sd
safetensors
endpoints_compatible
image-text-to-text
text-generation-inference
gu
ta
en
or
bn
te
pa
hi
mr
ml
kn
gemma3
as
doi
mni
ne
ur
sat
mai
gom
base_model:google/gemma-3-4b-it
license:gpl-3.0
ks
sa
  • See Upvoters1
  • Downloads87
  • File Size0
  • Views1,345
Updated 10 month(s) ago
SARVAM AI
View Details
share
sarvam-1
India's first indic model, pretrained on 4 trillion tokens
  • See Upvoters3
  • Downloads251
  • File Size0
  • Views4,814
Updated 1 year(s) ago
SARVAM AI
View Details
share
shuka-v1
Multilingual audio to text model
audio-llms
  • See Upvoters3
  • Downloads105
  • File Size0
  • Views1,990
Updated 1 year(s) ago
SARVAM AI
View Details
share

© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.