---
title: Bharat-Tiny-LLM
emoji: 🤖
colorFrom: blue
colorTo: indigo
sdk: docker
pinned: true
license: apache-2.0
---

# 🇮🇳 Bharat-Tiny-LLM

**Hinglish AI — trained on a Mac Mini M4, runs on ₹8,000 phones.**

A live demo of [Bharat-Tiny-LLM](https://huggingface.co/eulogik/Bharat-Tiny-LLM): India's first
native edge AI for **Hinglish & Hindi**, fully offline and open-weight (Apache-2.0).

> Built by [eulogik](https://eulogik.com)

## Try it

Type in Hinglish or Hindi — the model replies in the same register. Use the **Settings**
accordion to tune temperature / max tokens (defaults are the recommended clean-output values).

## Links

- 🤗 Model (MLX): https://huggingface.co/eulogik/Bharat-Tiny-LLM
- 🤗 GGUF (llama.cpp): https://huggingface.co/eulogik/Bharat-Tiny-LLM-GGUF
- 🤗 fp16 fused: https://huggingface.co/eulogik/Bharat-Tiny-LLM-fused
- 💻 Source: https://github.com/eulogik/Bharat-Tiny-LLM
- 📦 PyPI: https://pypi.org/project/bharat-tiny-llm/
- 🏢 Built by [eulogik](https://eulogik.com)

## Note on generation

This demo uses `temperature=0.3`, `top_p=0.85`, `repetition_penalty=1.25`,
`no_repeat_ngram_size=3` — the settings required for clean, in-script output from the
Qwen2.5 base. Higher temperatures produce garbled out-of-script tokens.