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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use moolvylabs/Morphy-Math-1.5B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf moolvylabs/Morphy-Math-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf moolvylabs/Morphy-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 serve -hf moolvylabs/Morphy-Math-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf moolvylabs/Morphy-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 moolvylabs/Morphy-Math-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf moolvylabs/Morphy-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 moolvylabs/Morphy-Math-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf moolvylabs/Morphy-Math-1.5B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/moolvylabs/Morphy-Math-1.5B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use moolvylabs/Morphy-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 "moolvylabs/Morphy-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": "moolvylabs/Morphy-Math-1.5B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/moolvylabs/Morphy-Math-1.5B-GGUF:Q4_K_M

Ollama
How to use moolvylabs/Morphy-Math-1.5B-GGUF with Ollama:
```
ollama run hf.co/moolvylabs/Morphy-Math-1.5B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use moolvylabs/Morphy-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 serve -hf moolvylabs/Morphy-Math-1.5B-GGUF:Q4_K_M

Configure the model in Pi

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

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use moolvylabs/Morphy-Math-1.5B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull moolvylabs/Morphy-Math-1.5B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Morphy-Math-1.5B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use moolvylabs/Morphy-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 serve -hf moolvylabs/Morphy-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 moolvylabs/Morphy-Math-1.5B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use moolvylabs/Morphy-Math-1.5B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf moolvylabs/Morphy-Math-1.5B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "moolvylabs/Morphy-Math-1.5B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Morphy-Math-1.5B is the third model in the Morphy lineup developed by the Moolvylabs team. Unlike previous text-focused versions, this model has undergone selective, highly targeted fine-tuning on complex advanced academic datasets. It is fully optimized for exceptional performance in higher sciences while remaining lightweight enough to run locally on consumer-grade hardware.

✨ Strengths (What the model excels at)

🧮 Higher Mathematics & Calculus — outstanding performance in solving university-level limits, improper integrals, derivatives, and infinite series step-by-step using strict Chain of Thought (CoT).
📐 Linear Algebra & Differential Equations — effortlessly handles non-linear differential equations (such as Bernoulli equations), spectral theorems, matrix eigenvalues, and eigenvectors.
⚛️ Quantum Computing & Physics — natively understands advanced physics, Dirac bra-ket notations, Pauli operators, and complex quantum state transformations.

⚠️ Important Features and Limitations (Disclaimer)

Since this model is deployed across various quantization formats to support low-end hardware, please keep the following nuances in mind:

🔬 Model Quantization Impact: The full FP16 and Q8_0 versions retain near 100% of the model's complex reasoning logic. However, aggressive bit-compression variants (Q4_K_M / Q5_K_M) may occasionally exhibit minor logical degradation or index confusion on highly abstract, multi-variable academic equations (e.g., advanced tensor calculus).
🌐 Language Nuance: For maximum accuracy in complex symbolic formulas and advanced scientific notations, prompting the model in English is highly recommended.

🛠️ Technical Specifications

Parameter	Value
Name	Morphy-Math-1.5B
Generation	Third model in the family
Base Model	Qwen2.5-Math-1.5B-Instruct
Data Type	Custom Higher Mathematics & Quantum Physics Paks
Purpose	Advanced Calculus / Tensor Analysis / Symbolic Reasoning

Downloads last month: 48

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

4-bit

5-bit

6-bit

8-bit