Instructions to use SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF",
	filename="Qwen2.5-Math-1.5B_Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M

Ollama
How to use SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF with Ollama:
```
ollama run hf.co/SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF to start chatting

Pi new

How to use SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF with Docker Model Runner:
```
docker model run hf.co/SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M
```

Lemonade

How to use SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-Math-1.5B-GGUF-Q4_K_M

List all available models

lemonade list

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.

Downloads last month: 6

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

4-bit

5-bit

Model tree for SandLogicTechnologies/Qwen2.5-Math-1.5B-GGUF

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-Math-1.5B

Quantized

(14)

this model