Instructions to use ofa12334/rabmac-pr1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ofa12334/rabmac-pr1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ofa12334/rabmac-pr1-GGUF",
	filename="rabmac-pr1-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ofa12334/rabmac-pr1-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 ofa12334/rabmac-pr1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ofa12334/rabmac-pr1-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 ofa12334/rabmac-pr1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ofa12334/rabmac-pr1-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 ofa12334/rabmac-pr1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ofa12334/rabmac-pr1-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 ofa12334/rabmac-pr1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ofa12334/rabmac-pr1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ofa12334/rabmac-pr1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use ofa12334/rabmac-pr1-GGUF with Ollama:
```
ollama run hf.co/ofa12334/rabmac-pr1-GGUF:Q4_K_M
```

Unsloth Studio

How to use ofa12334/rabmac-pr1-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 ofa12334/rabmac-pr1-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 ofa12334/rabmac-pr1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ofa12334/rabmac-pr1-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use ofa12334/rabmac-pr1-GGUF with Docker Model Runner:
```
docker model run hf.co/ofa12334/rabmac-pr1-GGUF:Q4_K_M
```

Lemonade

How to use ofa12334/rabmac-pr1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ofa12334/rabmac-pr1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.rabmac-pr1-GGUF-Q4_K_M

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

rabmac-pr1 — Gemma-3-27B GGUF

Offline device-manager AI assistant fine-tuned on Linux/macOS/Windows system administration tasks. Supports Turkish and English. Based on google/gemma-3-27b-it with QLoRA fine-tuning.

Files

File	Quant	Size	Use case
`rabmac-pr1-Q4_K_M.gguf`	Q4_K_M	~16 GB	Recommended — best quality/size ratio
`rabmac-pr1-Q8_0.gguf`	Q8_0	~29 GB	High quality — for systems with 32+ GB RAM

Usage

llama-cli -m rabmac-pr1-Q4_K_M.gguf -p "List all running processes"

Downloads last month: -

GGUF

Model size

27B params

Architecture

gemma3

Hardware compatibility

4-bit

8-bit

Inference Providers NEW

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

Model tree for ofa12334/rabmac-pr1-GGUF

Base model

google/gemma-3-27b-pt

Finetuned

google/gemma-3-27b-it

Quantized

(140)

this model