Instructions to use Nathan-Maine/cmmc-expert-12b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nathan-Maine/cmmc-expert-12b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Nathan-Maine/cmmc-expert-12b",
	filename="cmmc-expert-12b-q5_k_m.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Nathan-Maine/cmmc-expert-12b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Nathan-Maine/cmmc-expert-12b:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf Nathan-Maine/cmmc-expert-12b:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Nathan-Maine/cmmc-expert-12b:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf Nathan-Maine/cmmc-expert-12b:Q5_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 Nathan-Maine/cmmc-expert-12b:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf Nathan-Maine/cmmc-expert-12b:Q5_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 Nathan-Maine/cmmc-expert-12b:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Nathan-Maine/cmmc-expert-12b:Q5_K_M

Use Docker

docker model run hf.co/Nathan-Maine/cmmc-expert-12b:Q5_K_M

LM Studio
Jan
Ollama
How to use Nathan-Maine/cmmc-expert-12b with Ollama:
```
ollama run hf.co/Nathan-Maine/cmmc-expert-12b:Q5_K_M
```

Unsloth Studio

How to use Nathan-Maine/cmmc-expert-12b 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 Nathan-Maine/cmmc-expert-12b 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 Nathan-Maine/cmmc-expert-12b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Nathan-Maine/cmmc-expert-12b to start chatting

Docker Model Runner
How to use Nathan-Maine/cmmc-expert-12b with Docker Model Runner:
```
docker model run hf.co/Nathan-Maine/cmmc-expert-12b:Q5_K_M
```

Lemonade

How to use Nathan-Maine/cmmc-expert-12b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Nathan-Maine/cmmc-expert-12b:Q5_K_M

Run and chat with the model

lemonade run user.cmmc-expert-12b-Q5_K_M

List all available models

lemonade list

CMMC Expert 12B

A compliance-specialized large language model fine-tuned by Nathan Maine for U.S. defense and regulated-industry cybersecurity compliance: CMMC 2.0, NIST SP 800-171 / 172 / 53, HIPAA, and DFARS.

Fine-tuned with QLoRA on an NVIDIA DGX Spark (GB10) over a curated, provenance-tracked compliance instruction dataset, and shipped as a quantized GGUF for fully local, air-gapped inference via Ollama or llama.cpp, with no cloud dependency.

Model details

Base model: Gemma 3 12B (Instruct)
Method: QLoRA (4-bit NF4)
Format: GGUF q5_k_m (~8.5 GB)
Domain: CMMC 2.0, NIST 800-171 / 172 / 53, HIPAA, DFARS
Training hardware: NVIDIA DGX Spark (GB10, 128 GB)

Usage (Ollama)

ollama run hf.co/Nathan-Maine/cmmc-expert-12b

Or download the GGUF and run it with llama.cpp.

Intended use and limitations

A research and drafting aid for compliance practitioners. It can be wrong; verify any control interpretation against the authoritative source documents before relying on it. Not legal advice.

License

This is a fine-tune of Google Gemma 3; use is subject to the Gemma Terms of Use.

Built by Nathan Maine. Training data and evaluation benchmarks: https://huggingface.co/Nathan-Maine . Pipeline and training code: https://github.com/NathanMaine/cmmc-compliance-ai-model

Downloads last month: 5

GGUF

Model size

12B params

Architecture

gemma3

Hardware compatibility

5-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Nathan-Maine/cmmc-expert-12b

Base model

google/gemma-3-12b-pt

Finetuned

google/gemma-3-12b-it

Quantized

(152)

this model