Instructions to use kreier/gemma3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kreier/gemma3 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="kreier/gemma3",
	filename="gemma-3-4b-it-q4_0.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 kreier/gemma3 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 kreier/gemma3:Q4_0
# Run inference directly in the terminal:
llama cli -hf kreier/gemma3:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kreier/gemma3:Q4_0
# Run inference directly in the terminal:
llama cli -hf kreier/gemma3:Q4_0

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 kreier/gemma3:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf kreier/gemma3:Q4_0

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 kreier/gemma3:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kreier/gemma3:Q4_0

Use Docker

docker model run hf.co/kreier/gemma3:Q4_0

LM Studio
Jan
Ollama
How to use kreier/gemma3 with Ollama:
```
ollama run hf.co/kreier/gemma3:Q4_0
```

Unsloth Studio

How to use kreier/gemma3 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 kreier/gemma3 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 kreier/gemma3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kreier/gemma3 to start chatting

Atomic Chat new
Docker Model Runner
How to use kreier/gemma3 with Docker Model Runner:
```
docker model run hf.co/kreier/gemma3:Q4_0
```

Lemonade

How to use kreier/gemma3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kreier/gemma3:Q4_0

Run and chat with the model

lemonade run user.gemma3-Q4_0

List all available models

lemonade list

This is just a reupload of the gemma-3-4b-it-qat-q4_0 model. It can be installed by ollama run hf.co/kreier/gemma3.

The reason for this reupload is the conflicting login requirements for huggingface when downloading the original model and the use of huggingface-cli. I'm logged in in both and have access, but the combination does not work.

It is different from the general gemma3 model in that it is a 4B instruction-tuned version of the Gemma 3 model in GGUF format using Quantization Aware Training (QAT). The GGUF corresponds to Q4_0 quantization.

See more details here: https://huggingface.co/google/gemma-3-4b-it-qat-q4_0-gguf. It states: