sarvamai/sarvam-translate

translation model by sarvamai

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

<a href="https://dashboard.sarvam.ai/translate" Sarvam-Translate is an advanced translation model built by Sarvam AI in partnership with AI4Bharat, specifically designed for comprehensive, document-level translation across the 22 official Indian languages, built on Gemma3-4B-IT. It addresses modern translation needs by moving beyond isolated sentences to handle long-context inputs, diverse content types, and various formats. Sarvam-Translate aims to provide high-quality, contextually aware translations for Indian languages, which have traditionally lagged behind high-resource languages in LLM performance. Learn more about Sarvam-Translate in our detailed blog post. Assamese, Bengali, Bodo, Dogri, Gujarati, English, Hindi,…

sarvamai/sarvam-translate on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-10-27T23:38:51.595Z

Inside the original model card — Document outline
  1. Sarvam-Translate
  2. Key Features
  3. Supported languages list
  4. Supported directions
  5. Quickstart
  6. vLLM Deployment
  7. Server:
  8. Client:
  9. With Sarvam APIs

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: gpl-3.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

sarvamai/sarvam-translate is a translation model repository published by sarvamai on Hugging Face. The source reports the transformers library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
translation
Library
transformers
Recent downloads (30 days)
6,043
Cumulative likes
164
Hugging Face trending score
1
Reported safetensors parameters
4,300,079,472
Architecture
Gemma3ForConditionalGeneration
License
gpl-3.0
Access
Not gated by Hugging Face
Created
2025-06-07T10:13:56.000Z
Last modified
2026-07-13T11:49:53.000Z

Compatibility and lineage

Reported languages: as, bn, brx, doi, gom, gu, en, hi, kn, ks, mai, ml, mni, mr, ne, or, pa, sa, sat, sd, ta, te, ur

Reported base models: google/gemma-3-4b-it

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-10-31T06:53:34.747Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models

google-t5/t5-small

google-t5/t5-base

facebook/nllb-200-distilled-600M

Helsinki-NLP/opus-mt-nl-en

Helsinki-NLP/opus-mt-zh-en

facebook/nllb-200-distilled-1.3B