Indic-mobile is a 0.5B parameter language model built completely from scratch — no fine-tuning, no adapter on top of an existing checkpoint. Every weight was pretrained from zero, purpose-built for all 22 officially recognized Indian languages and designed for efficient deployment on mobile and edge devices.
India has 1.4 billion people and 22 officially recognized languages — yet most language models were never built with this diversity in mind. Indic-mobile is designed to change that:
Built from scratch — not a fine-tune or adapter on an existing English-centric model
Truly multilingual — trained across all 22 Indian languages from the ground up
Mobile-first — 0.5B parameters means it runs efficiently on edge devices and smartphones
Open source — weights, architecture, and everything else, freely available
Usage
Load with 🤗 Transformers
python
1from transformers import AutoTokenizer, AutoModelForCausalLM
2import torch
34model_id ="RockySinghRajput/Indic-mobile"56tokenizer = AutoTokenizer.from_pretrained(model_id)7model = AutoModelForCausalLM.from_pretrained(8 model_id,9 torch_dtype=torch.bfloat16,10 device_map="auto"11)1213prompt ="भारत एक विविधताओं से भरा देश है।"# Example Hindi prompt14inputs = tokenizer(prompt, return_tensors="pt").to(model.device)1516outputs = model.generate(**inputs, max_new_tokens=100)17print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Run with Ollama
ollama run hf.co/RockySinghRajput/Indic-mobile
Run with vLLM
vllm serve RockySinghRajput/Indic-mobile
Model Architecture
Architecture: Custom (trained from scratch)
Parameters: 0.5B
Precision: BF16
Training: Pretrained from scratch (no base model used)
Objective: Causal language modeling across 22 Indic languages
Intended Uses
Direct Use
Text generation in any of the 22 official Indian languages
Multilingual Indic chatbots and assistants
On-device / mobile NLP applications
Low-resource language research and experimentation
Downstream Use
Fine-tuning for specific Indic language tasks (classification, summarization, translation, QA)
Integration into larger Indic NLP pipelines
RAG (Retrieval-Augmented Generation) systems for Indian language content
Out-of-Scope Use
High-stakes decision making without human oversight
Generation of harmful, misleading, or abusive content in any language
Tasks requiring deep factual accuracy without verification
Bias, Risks, and Limitations
As a small 0.5B model, it may struggle with complex reasoning or long-form generation compared to larger models
Training data distribution across all 22 languages may not be perfectly balanced; lower-resource languages may underperform
Like all language models, it may reflect biases present in the training data
Not intended for use in safety-critical or high-stakes applications without further evaluation and fine-tuning
Recommendations
Users should evaluate the model on their specific use case and language before deployment, particularly for lower-resource Indic languages.
Evaluation
Formal benchmarks are in progress. Community evaluations and feedback are welcome — please open a Discussion to share results!
Citation
If you use Indic-mobile in your research or projects, please consider citing:
bibtex
1@misc{indic-mobile-2025,
2 author = {Rocky Singh Rajput},
3 title = {Indic-mobile: A 0.5B Language Model for All 22 Official Indian Languages},
4 year = {2025},
5 publisher = {Hugging Face},
6 url = {https://huggingface.co/RockySinghRajput/Indic-mobile}
7}
