Qalb-1.0-8B-Instruct (FP16)

Qalb is the state-of-the-art Urdu Large Language Model (LLM), designed for 230M+ speakers. It was developed through systematic continued pre-training on 1.97 billion Urdu tokens, followed by rigorous instruction fine-tuning to ensure high performance in native Urdu script.

Performance Benchmarks

Qalb-1.0-8B outperforms existing models across various linguistic and reasoning tasks:

Usage Guide

Terminal (Bash)

To run the model directly in your terminal:

ollama run enstazao/qalb:8b-instruct-fp16

Python API

Use the ollama Python library for integration:

import ollama

response = ollama.chat(model='enstazao/qalb:8b-instruct-fp16', messages=[
  {
    'role': 'user',
    'content': 'پاکستان کا قومی کھیل کیا ہے؟',
  },
])

print(response['message']['content'])

Curl (REST API)

curl http://localhost:11434/api/generate -d '{
  "model": "enstazao/qalb:8b-instruct-fp16",
  "prompt": "پاکستان کا قومی کھیل کیا ہے؟",
  "stream": false
}'

Limitation & Bias

While Qalb has been trained to be helpful and harmless, it may still reflect biases present in the training data. Users should fact-check critical information, especially in medical, legal, or religious contexts.

Citation

If you use Qalb in your research, please cite:

@article{qalb2025,
  title={Qalb: Largest State-of-the-Art Urdu Large Language Model for 230M Speakers with Systematic Continued Pre-training},
  author={Hassan, Muhammad Taimoor and Ahmed, Jawad and Awais, Muhammad},
  journal={arXiv preprint arXiv:2601.08141},
  year={2026},
  eprint={2601.08141},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={[https://arxiv.org/abs/2601.08141](https://arxiv.org/abs/2601.08141)},
  doi={10.48550/arXiv.2601.08141}
}