Instructions to use DQN-Labs-Community/dqnMath-v1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DQN-Labs-Community/dqnMath-v1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="DQN-Labs-Community/dqnMath-v1-GGUF",
	filename="DQN-Math-v1.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 DQN-Labs-Community/dqnMath-v1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf DQN-Labs-Community/dqnMath-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DQN-Labs-Community/dqnMath-v1-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 DQN-Labs-Community/dqnMath-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DQN-Labs-Community/dqnMath-v1-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 DQN-Labs-Community/dqnMath-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf DQN-Labs-Community/dqnMath-v1-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 DQN-Labs-Community/dqnMath-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DQN-Labs-Community/dqnMath-v1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/DQN-Labs-Community/dqnMath-v1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use DQN-Labs-Community/dqnMath-v1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DQN-Labs-Community/dqnMath-v1-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": "DQN-Labs-Community/dqnMath-v1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DQN-Labs-Community/dqnMath-v1-GGUF:Q4_K_M

Ollama
How to use DQN-Labs-Community/dqnMath-v1-GGUF with Ollama:
```
ollama run hf.co/DQN-Labs-Community/dqnMath-v1-GGUF:Q4_K_M
```

Unsloth Studio new

How to use DQN-Labs-Community/dqnMath-v1-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 DQN-Labs-Community/dqnMath-v1-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 DQN-Labs-Community/dqnMath-v1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DQN-Labs-Community/dqnMath-v1-GGUF to start chatting

Pi new

How to use DQN-Labs-Community/dqnMath-v1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf DQN-Labs-Community/dqnMath-v1-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": "DQN-Labs-Community/dqnMath-v1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use DQN-Labs-Community/dqnMath-v1-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 DQN-Labs-Community/dqnMath-v1-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 DQN-Labs-Community/dqnMath-v1-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use DQN-Labs-Community/dqnMath-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/DQN-Labs-Community/dqnMath-v1-GGUF:Q4_K_M
```

Lemonade

How to use DQN-Labs-Community/dqnMath-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DQN-Labs-Community/dqnMath-v1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.dqnMath-v1-GGUF-Q4_K_M

List all available models

lemonade list

dqnMath-v1

dqnMath-v1 is a 4B-parameter language model designed for fast, clear, and reliable mathematical problem solving.

It focuses on solving problems efficiently, with concise steps and minimal unnecessary explanation. It's optimized for solving daily mathematical problems quickly and efficiently, with minimal token count.

Model Description

Model type: Causal Language Model
Parameters: 4B
Primary use: Mathematical problem solving
Style: Direct answers with optional, minimal step-by-step reasoning

dqnMath v1 4B is optimized for clarity and speed rather than long-form reasoning or benchmark performance.

Intended Uses

Direct Use

Solving school-level math problems
Performing quick calculations
Explaining basic mathematical steps
Assisting with homework and practice
Low to moderate reasoning-heavy math

Key Characteristics

Produces concise and readable solutions
Prioritizes correctness over verbosity
Uses structured reasoning when needed
Designed for consistent outputs across similar problems
Reliable and minimal hallucination

Example

Input

Solve: 2x + 3 = 7

Output

2x = 4
x = 2

Input

Convert 0.333... to a fraction

Output

Let x = 0.333...

10x = 3.333...
10x - x = 3
9x = 3
x = 1/3

Usage

This model is available on many platforms and is compatible with many formats!

The GGUF format is compatible with llama.cpp and LM Studio. Other formats include MLX (LM Studio, optimized for Apple devices), and HF (universal compatibility).

Training Details

dqnMath-v1 is fine-tuned for structured mathematical reasoning and concise problem-solving.

The training process emphasizes:

Step-by-step clarity
Reduced verbosity
Reliable first-attempt answers

Limitations

Limited performance on advanced mathematics
Not optimized for non-mathematical domains
May simplify explanations rather than explore deeply

Efficiency

dqnMath-v1 is designed to run efficiently on consumer hardware, with support for quantized formats.

License

Apache 2.0

Author

Developed by DQN Labs. Huge thanks to the team at mradermacher for quantizing this model! This model card was generated with the help of dqnGPT v0.2!

Downloads last month: 43

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

16-bit

Collection including DQN-Labs-Community/dqnMath-v1-GGUF

dqnMath-v1

Collection

dqnMath-v1 is an efficient 4B math model, trained for token-efficient math solving, targeted at daily-use, grade school math, for local deployment. • 2 items • Updated Apr 7