SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF

Quantized Qwen2.5-Math-1.5B Model

This repository hosts the Qwen2.5-Math-1.5B language model an optimized transformer designed to handle advanced mathematical reasoning, symbolic problem solving, and step-by-step solution generation. Built for educational assistance, competitive mathematics settings, and research in formal reasoning, the model offers strong performance while maintaining efficient deployment requirements.

Model Overview

• Base-Model: Qwen2.5-Math-1.5B
• Original-Model: Qwen2.5-1.5B
• Architecture: Decoder-only transformer
• Quantized Versions:
  • Q4_K_M (4-bit quantization)
  • Q5_K_M (5-bit quantization)
• Modalities: Text
• Developer: Qwen
• Language: English
• License: Apache 2.0
• Input/Output Format: Instruction-tuned conversational format

Quantization Details

Q4_K_M Version

• Approx. ~70% size reduction
• Lower memory footprint (~940 MB)
• Best suited for deployment on edge devices or low-resource GPUs
• Slight performance degradation in complex reasoning scenarios

Q5_K_M Version

• Approx. ~66% size reduction
• Higher fidelity (~1.04 GB)
• Better performance retention, recommended when quality is a priority

Dataset & Training

• The model is trained on curated mathematics-focused datasets consisting of:
• Textbooks & structured solutions
• Problem-answer pairs and mathematical explanations
• High-difficulty reasoning tasks used in competitive examination preparation

Key Strengths

• Strong capability for multi-step reasoning and deriving structured solutions
• Generates stepwise explanations rather than single-answer outputs
• Suitable for high-performance inference on GPUs and high-end CPUs
• Rich instruction-following behavior for math problem sets and tutoring systems
• Works effectively with chain-of-thought prompting strategies

Intended Use

This model is designed for scenarios where mathematical reasoning is critical, such as:

• Learning platforms & tutoring assistants : Automated step-by-step math explainer systems
• Academic research : Algorithms and experiments involving symbolic reasoning
• STEM educational tools : Training models targeted at competitive exam preparation
• Conversational reasoning agents : Math-focused dialog systems for structured question answering

Usage

This model is meant for mathematical guidance and should not replace expert professional judgement in scientific or financial applications.

llama.cpp (text-only)

./llama-cli -hf SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF -p "Explain Taylor series"

Acknowledgments

These quantized models are based on the original work by Qwen development team.

Special thanks to:

• The Qwen team for developing and releasing the Qwen2.5-Math-1.5B model.
• Georgi Gerganov and the entire llama.cpp open-source community for enabling efficient model quantization and inference via the GGUF format.

Contact

For any inquiries or support, please contact us at support@sandlogic.com or visit our Website.