Instructions to use theaicmo/MOM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theaicmo/MOM with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="theaicmo/MOM",
	filename="qwen3-14b.Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use theaicmo/MOM 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 theaicmo/MOM:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf theaicmo/MOM:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf theaicmo/MOM:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf theaicmo/MOM: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 theaicmo/MOM:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf theaicmo/MOM: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 theaicmo/MOM:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf theaicmo/MOM:Q4_K_M

Use Docker

docker model run hf.co/theaicmo/MOM:Q4_K_M

LM Studio
Jan

vLLM

How to use theaicmo/MOM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/theaicmo/MOM:Q4_K_M

Ollama
How to use theaicmo/MOM with Ollama:
```
ollama run hf.co/theaicmo/MOM:Q4_K_M
```

Unsloth Studio

How to use theaicmo/MOM 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 theaicmo/MOM 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 theaicmo/MOM to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for theaicmo/MOM to start chatting

How to use theaicmo/MOM with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf theaicmo/MOM: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": "theaicmo/MOM:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use theaicmo/MOM with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf theaicmo/MOM: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 theaicmo/MOM:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use theaicmo/MOM with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf theaicmo/MOM: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 "theaicmo/MOM: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"

Docker Model Runner
How to use theaicmo/MOM with Docker Model Runner:
```
docker model run hf.co/theaicmo/MOM:Q4_K_M
```

Lemonade

How to use theaicmo/MOM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull theaicmo/MOM:Q4_K_M

Run and chat with the model

lemonade run user.MOM-Q4_K_M

List all available models

lemonade list

MOM — Marketing Open Model

The open-source LLM purpose-built for marketing professionals.

MOM is a fine-tuned Qwen3-14B model trained on marketing Q&A pairs covering the full spectrum of modern marketing — from brand strategy and positioning to paid media, SEO, analytics, and team management. Built by The AI CMO.

Just run: ollama run hf.co/theaicmo/MOM

Highlights

Base model: Qwen3-14B (4-bit QLoRA via Unsloth)
Training data: Curated marketing instruction pairs generated from authoritative marketing sources
16 marketing domains covered in depth
Format: GGUF Q4_K_M — runs locally via Ollama, llama.cpp, LM Studio
License: MIT — fully open, commercial use welcome

Quick Start

# Run with Ollama
ollama run hf.co/theaicmo/MOM

Or download the GGUF file and load it in llama.cpp, LM Studio, or any GGUF-compatible runtime.

Example Prompts

What frameworks should I use to position a B2B SaaS product in a crowded market?

How do I structure a marketing budget for a Series A startup with $2M annual spend?

What KPIs should I track for a content marketing program and how do I tie them to revenue?

How should I organize a marketing team of 15 people across brand, growth, and product marketing?

Training Details

Method: QLoRA 4-bit fine-tuning with Unsloth
LoRA rank: 32 | Alpha: 32 | Dropout: 0
Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Epochs: 3 | Batch size: 8 (2 × 4 grad accum) | LR: 2e-4 (cosine schedule)
Quantization: GGUF Q4_K_M via llama.cpp

About The AI CMO

The AI CMO builds AI-powered tools for marketing leaders. MOM is our first open model — designed to give every marketer access to CMO-level strategic thinking.

License

MIT — use it however you want, commercially or otherwise.

Citation

@misc{mom2026,
  title={MOM: Marketing Open Model},
  author={The AI CMO},
  year={2026},
  url={https://huggingface.co/theaicmo/MOM}
}

Downloads last month: 7

GGUF

Model size

15B params

Architecture

qwen3

Hardware compatibility

4-bit

Model tree for theaicmo/MOM

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Adapter

(479)

this model