Instructions to use DQN-Labs-Community/dqnMath-v0.3-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DQN-Labs-Community/dqnMath-v0.3-1.5B with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("DQN-Labs-Community/dqnMath-v0.3-1.5B")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

Pi new

How to use DQN-Labs-Community/dqnMath-v0.3-1.5B with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "DQN-Labs-Community/dqnMath-v0.3-1.5B"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "DQN-Labs-Community/dqnMath-v0.3-1.5B"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use DQN-Labs-Community/dqnMath-v0.3-1.5B with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "DQN-Labs-Community/dqnMath-v0.3-1.5B"

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-v0.3-1.5B

Run Hermes

hermes

MLX LM

How to use DQN-Labs-Community/dqnMath-v0.3-1.5B with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "DQN-Labs-Community/dqnMath-v0.3-1.5B"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "DQN-Labs-Community/dqnMath-v0.3-1.5B"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "DQN-Labs-Community/dqnMath-v0.3-1.5B",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

dqnMath v0.3 1.5B

Overview

dqnMath v0.3 1.5B is a math-focused language model designed for strong performance in algebra, arithmetic, and structured reasoning tasks. It is part of the DQN Labs model suite and is optimized for efficiency on consumer hardware.

Model Details

Model Name: dqnMath v0.3
Parameters: 1.5B
Architecture: Dense Transformer
Domain: Mathematics, reasoning
Version: v0.3

Capabilities

Solves algebraic equations
Performs step-by-step reasoning
Handles arithmetic and symbolic problems
Interprets math word problems

Limitations

Weak in advanced mathematics (calculus, proofs)
Limited coding ability
Not suitable for general chat or creative writing
May produce incorrect reasoning on complex problems
Is NOT a thinking model.

Notes

Part of the DQN Labs model family:

dqnGPT
dqnCode
dqnWrite

By DQN Labs. Local AI for everyone.

Downloads last month: -

Safetensors

Model size

2B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for DQN-Labs-Community/dqnMath-v0.3-1.5B

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Finetuned

(1579)

this model

Quantizations

1 model