Models/Airavata
Airavata mark

Airavata

Fine-tunedOpen-sourceEnglishहिन्दी

In plain words

Airavata is a Hindi instruction model that follows everyday requests clearly. It is open-source and tuned to be helpful and polite, making it a reliable choice for Hindi writing, answers, and assistance.

How to use it

Before you start
Prerequisites required to run the model locally

To run Airavata 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.
  1. For 3B models: Minimum 8 GB of RAM.
  2. For 7B–8B models: Minimum 16 GB of RAM.
  3. 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 Airavata using below mentioned steps.

1
Downloading the Airavata GGUF file

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

2
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/sam749/Airavata-GGUF


3
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)
4
Start chatting

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

5
Exit the chat

To end the session, type:

/bye

Then press Enter. Alternatively, press Ctrl+C to exit immediately.

Languages & scripts supported

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

English Englishहिन्दी Hindi+ Roman & code-mixed

Strengths & limits

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

Good at
Clear, polite Hindi answers
Following everyday instructions
Free and open to run local
Backed by trusted research
Where it struggles
!Does not support many languages
!Smaller in parameter size than massive frontier models
!Up-to-date facts after training
!Heavy reasoning or maths

About the maker

Who builds and maintains Airavata.

AI4Bharat logo
AI4Bharat
6 models

AI4Bharat is an open-source research lab at IIT Madras dedicated to advancing AI for Indian languages. Its freely released datasets, benchmarks, and models — like Airavata and the IndicTrans translation series — are widely used across research and industry.

Compare

More like this

Comparable models you may also want to try.