md-nishat-008/TigerLLM-1B-it

Hugging Face
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1BQuant:BF16Context Size:32kPublished:Sep 9, 2025License:cc-by-4.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Warm

TigerLLM-1B-it is a 1.0 billion parameter instruction-tuned causal language model developed by Nishat Raihan and Marcos Zampieri at George Mason University, built on the Gemma 3 architecture. This compact model is primarily designed for instruction-following tasks in Bangla, including question answering, explanation, rewriting, summarization, and translation. It is optimized for deployment on laptop GPUs or CPUs, offering strong performance in Bangla language processing within a small footprint.

Loading preview...

TigerLLM-1B-it: A Compact Bangla Instruction-Tuned LLM

TigerLLM-1B-it is a 1.0 billion parameter instruction-tuned language model, part of the TigerLLM family developed by Nishat Raihan and Marcos Zampieri. Built on the Gemma 3 architecture, this model is specifically designed for instruction-following tasks in Bangla, offering capabilities such as question answering, explanation, rewriting, summarization, and translation. It features a substantial context length of 32,768 tokens and is optimized for efficient deployment on devices with limited resources, like laptop GPUs or CPUs.

Key Capabilities

  • Bangla Instruction Following: Excels at understanding and executing instructions in Bangla across various tasks.
  • Compact and Efficient: With 1.0 billion parameters, it's suitable for local deployment and resource-constrained environments.
  • Enhanced Performance: This Gemma 3-based version scores 2-4% higher on Bangla benchmarks compared to its deprecated LLaMA-based predecessor.
  • Multilingual Support: Primarily focused on Bangla, with additional support for English.
  • ACL 2025 Paper: The model is part of research presented at ACL 2025, demonstrating its academic backing and rigorous development.

Good For

  • Bangla Language Applications: Ideal for developers building applications requiring robust Bangla text generation and understanding.
  • Resource-Constrained Deployments: Suitable for use cases where larger models are impractical due to hardware limitations.
  • Instruction-Following Tasks: Effective for tasks like chatbots, content generation, and summarization in Bangla.
  • Research and Development: Provides a strong baseline for further research into low-resource language models, particularly for Bangla.

Finetunes
1 models