Indic LM Platform

In plain words

BharatGPT is CoRover.ai's sovereign AI foundational model, natively supporting 12+ Indian languages for enterprise integration.

How to use it

Before you start

Prerequisites required to run the model locally

To run BharatGPT model locally on your computer, the following requirements must be met:

Install and set up Ollama.
Ensure your computer has enough RAM to run the model you plan to download.

For 3B models: Minimum 8 GB of RAM.
For 7B–8B models: Minimum 16 GB of RAM.
For 13B–32B models: Minimum 32 GB of RAM.

Quantised model: It is recommended to use 4-bit Quantized, K-measurement, Small model format. Easy to download and to run your system.
Storage: 5 to 20 GB of free SSD space to store downloaded model files.
Interface: Terminal or command line utility to run basic startup prompts.

No technical setup needed — anyone can try BharatGPT using below mentioned steps.

Downloading the BharatGPT GGUF file

Go to the BharatGPT GGUF file on Hugging Face. Click the copy icon next to the repository name to copy the model path. (See image below.)

Run the model in your terminal

Open a terminal window and run the following command and paste the copied GGUF repository as mentioned below:

ollama run hf.co/PASTE_THE_COPIED_HERE

Press Enter.

Note: After pasting the repository, your command will look like this:

ollama run hf.co/QuantFactory/BharatGPT-3B-Indic-GGUF

Wait for the model to load

Ollama will download and initialise the model. Once ready, you'll see the following prompt:

>>> Send a message (/? for help)

Start chatting

Type your message at the prompt and press Enter to interact with the model.

Exit the chat

To end the session, type:

/bye

Then press Enter.

Languages & scripts supported

Works in these languages, in both native script and Roman typing.

हिन्दी Hindiमराठी Marathiગુજરાતી Gujaratiதமிழ் Tamilతెలుగు Teluguಕನ್ನಡ Kannadaଓଡ଼ିଆ Odiaবাংলা Bengaliമലയാളം Malayalamਪੰਜਾਬੀ Punjabiঅসমীয়া Assamese+ Roman & code-mixed

Strengths & limits

An honest look at what it does well and where it struggles.

Good at

✓Native language processing

✓Text generation

Where it struggles

!Highly complex code generation

!Low-resource dialects without fine-tuning

Technical details & licence

Training dataTrained on authentic Indian conversational data across 12 languages, supported by the Government of India's iHub Anubhuti IIITD Foundation and Department of Science & Technology; a Gemma-based e-governance variant is also in development.

SizeThe public research checkpoint, BharatGPT-3B-Indic, is a ~3.2B-parameter LLaMA-based model fine-tuned for Indic conversations; the flagship enterprise BharatGPT platform's underlying model size is not publicly disclosed.

LicenceThe enterprise BharatGPT platform is proprietary; the BharatGPT-3B-Indic research weights on Hugging Face are licensed for academic/research use only — commercial use requires contacting CoRover directly.

Commercial costContact for enterprise pricing; free tier available for platform sign-up; research weights free for non-commercial use

Version historyBharatGPT-3B-Indic · 2024 — Sovereign transformer-based Indic LLM released on Hugging FaceBharatGPT Mini · June 2025 — 534M-parameter offline/edge model unveiled at VivaTech 2025, built with Intel

About the maker

Who builds and maintains BharatGPT.

CoRover.ai

1 models

CoRover.ai is an enterprise conversational-AI company founded in 2016, whose chatbot and virtual-assistant platform is used by large banks, government bodies, and other high-scale services. BharatGPT is its generative-AI layer, extending that platform with multilingual voice and text support across a dozen-plus Indian languages.

View their models →See all organisations →