Indian Flag
Government Of India
A-
A
A+
ORGANISATION

sarvamM

Multilingual, hybrid-reasoning, text-only language model built on Mistral-Small

About Model

sarvam-m is a multilingual, hybrid-reasoning, text-only language model built on Mistral-Small. This post-trained version delivers exceptional improvements over the base model:

  • +20% average improvement on Indian language benchmarks

  • +21.6% enhancement on math benchmarks

  • +17.6% boost on programming benchmarks

Performance gains are even more impressive at the intersection of Indian languages and mathematics, with an outstanding +86% improvement in romanized Indian language GSM-8K benchmarks.

Learn more about sarvam-m in our detailed blog - https://www.sarvam.ai/blogs/sarvam-m

Key Features

  • Hybrid Thinking Mode: A single versatile model supporting both "think" and "non-think" modes. Use the think mode for complex logical reasoning, mathematical problems, and coding tasks, or switch to non-think mode for efficient, general-purpose conversation.

  • Advanced Indic Skills: Specifically post-trained on Indian languages alongside English, embodying a character that authentically reflects and emphasizes Indian cultural values.

  • Superior Reasoning Capabilities: Outperforms most similarly-sized models on coding and math benchmarks, demonstrating exceptional reasoning abilities.

  • Seamless Chatting Experience: Full support for both Indic scripts and romanized versions of Indian languages, providing a smooth and accessible multilingual conversation experience.


sarvamM

Metadata Metadata

Apache 2.0

sarvamai

Transformers

PyTorch

Open

Sarvam AI

Sector Agnostic

20/08/25 05:45:38

0

Activity Overview Activity Overview

  • Downloads1
  • Redirect 73
  • File Size 0
  • Views 1,666

Tags Tags

  • Transformers
  • safetensors
  • mistral
  • Text Generation
  • conversational
  • en
  • bn
  • hi
  • kn
  • gu
  • mr
  • ml
  • or
  • pa
  • 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

License Control License Control

Apache 2.0

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 Upvoters5
  • Downloads194
  • File Size59.92 GB
  • Views3,154
Updated 5 month(s) ago

SARVAM AI

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
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
license:apache-2.0
bo
  • See Upvoters9
  • Downloads628
  • File Size0
  • Views10,226
Updated 5 month(s) ago

SARVAM AI

sarvamM
Multilingual, hybrid-reasoning, text-only language model built on Mistral-Small
region:us
Transformers
safetensors
mistral
Text Generation
conversational
en
bn
hi
kn
gu
mr
ml
or
pa
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
  • See Upvoters1
  • Downloads73
  • File Size0
  • Views1,667
Updated 1 year(s) ago

SARVAM AI

sarvamtranslate
Translation model for 22 Indian Languages
endpoints_compatible
text-generation-inference
region:us
Transformers
safetensors
gemma3
image-text-to-text
Translation
as
bn
brx
doi
gom
gu
en
hi
kn
ks
mai
ml
mni
mr
ne
or
pa
sa
sat
sd
ta
te
ur
base_model:google/gemma-3-4b-it
base_model:finetune:google/gemma-3-4b-it
license:gpl-3.0
  • See Upvoters1
  • Downloads116
  • File Size0
  • Views2,159
Updated 1 year(s) ago

SARVAM AI

sarvam-1
India's first indic model, pretrained on 4 trillion tokens
  • See Upvoters3
  • Downloads287
  • File Size0
  • Views6,173
Updated 1 year(s) ago

SARVAM AI

shuka-v1
Multilingual audio to text model
audio-llms
  • See Upvoters3
  • Downloads116
  • File Size0
  • Views2,430
Updated 1 year(s) ago

SARVAM AI