Navarasa-2.0 is an instruction model that follows tasks across 15 Indian languages. Built by a community team, it is open-source and especially strong for South Indian languages like Telugu and Kannada.
To run Navrasa 2.0 locally on your computer, the following requirements must be met:
No technical setup needed — anyone can try Navarasa-2.0 using below mentioned steps.
Go to the Navrasa 2.0 GGUF file on Hugging Face. Click the copy icon next to the repository name to copy the model path. (See image below.)
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/https://huggingface.co/Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0-gguf
Ollama will download and initialise the model. Once ready, you'll see the following prompt:
>>> Send a message (/? for help)
Type your message at the prompt and press Enter to interact with the model.
To end the session, type:
/bye
Then press Enter.
Works in these languages, in both native script and Roman typing.
An honest look at what it does well and where it struggles.
Who builds and maintains Navarasa-2.0.
Telugu LLM Labs is a community-led effort building open models for Telugu and other Indian languages, often by carefully fine-tuning leading open models for strong local performance — a great example of community-driven Indic AI.
Comparable models you may also want to try.
