Instructions to use vininhosts/gemma3-12b-engineering-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vininhosts/gemma3-12b-engineering-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="vininhosts/gemma3-12b-engineering-GGUF",
	filename="gemma-3-12b-engineering-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 vininhosts/gemma3-12b-engineering-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vininhosts/gemma3-12b-engineering-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf vininhosts/gemma3-12b-engineering-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 vininhosts/gemma3-12b-engineering-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf vininhosts/gemma3-12b-engineering-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 vininhosts/gemma3-12b-engineering-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf vininhosts/gemma3-12b-engineering-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 vininhosts/gemma3-12b-engineering-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vininhosts/gemma3-12b-engineering-GGUF:Q4_K_M

Use Docker

docker model run hf.co/vininhosts/gemma3-12b-engineering-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use vininhosts/gemma3-12b-engineering-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vininhosts/gemma3-12b-engineering-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": "vininhosts/gemma3-12b-engineering-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vininhosts/gemma3-12b-engineering-GGUF:Q4_K_M

Ollama
How to use vininhosts/gemma3-12b-engineering-GGUF with Ollama:
```
ollama run hf.co/vininhosts/gemma3-12b-engineering-GGUF:Q4_K_M
```

Unsloth Studio new

How to use vininhosts/gemma3-12b-engineering-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 vininhosts/gemma3-12b-engineering-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 vininhosts/gemma3-12b-engineering-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vininhosts/gemma3-12b-engineering-GGUF to start chatting

Docker Model Runner
How to use vininhosts/gemma3-12b-engineering-GGUF with Docker Model Runner:
```
docker model run hf.co/vininhosts/gemma3-12b-engineering-GGUF:Q4_K_M
```

Lemonade

How to use vininhosts/gemma3-12b-engineering-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vininhosts/gemma3-12b-engineering-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma3-12b-engineering-GGUF-Q4_K_M

List all available models

lemonade list

gemma3-12b-engineering (GGUF Q4_K_M)

GGUF version of vininhosts/gemma3-12b-engineering.

Fine-tuned Gemma 3 12B IT for aerospace engineering, thermodynamics, advanced math, coding, finance, and 6 additional engineering disciplines. Quantized to Q4_K_M (~7.3 GB).

Model Details

Base model: google/gemma-3-12b-it
Fine-tuning: QLoRA, 4 sequential training passes, 23,850+ examples
Format: GGUF Q4_K_M
Size: ~7.3 GB

Usage (LM Studio / llama.cpp)

Download gemma-3-12b-engineering-Q4_K_M.gguf and load in LM Studio or any llama.cpp-compatible tool.

Recommended system prompt:

You are an expert aerospace engineer. Always reason step by step inside <think> tags before giving your final answer.

Run with llama.cpp:

llama-cli -m gemma-3-12b-engineering-Q4_K_M.gguf -p "A rocket nozzle has Pc=2MPa, Tc=3000K, M=20g/mol, gamma=1.3, exit Mach=3. Find exit pressure." -n 1024

Capabilities

Aerospace, thermodynamics, signals & systems, statics, dynamics, mechanics of materials, controls, manufacturing, mathematics, coding, finance.

See MLX version for full details.

License

Derived from Gemma 3 — subject to Gemma Terms of Use.

Downloads last month: 39

GGUF

Model size

13B params

Architecture

gemma3

Hardware compatibility

4-bit

Model tree for vininhosts/gemma3-12b-engineering-GGUF

Base model

google/gemma-3-12b-pt

Finetuned

google/gemma-3-12b-it

Quantized

(150)

this model