Instructions to use librepowerai/Gemma-3-4B-it-Power with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use librepowerai/Gemma-3-4B-it-Power with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="librepowerai/Gemma-3-4B-it-Power",
	filename="Gemma-3-4B-it-Q4_K_M-be.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 librepowerai/Gemma-3-4B-it-Power 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 librepowerai/Gemma-3-4B-it-Power:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf librepowerai/Gemma-3-4B-it-Power:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf librepowerai/Gemma-3-4B-it-Power:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf librepowerai/Gemma-3-4B-it-Power: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 librepowerai/Gemma-3-4B-it-Power:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf librepowerai/Gemma-3-4B-it-Power: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 librepowerai/Gemma-3-4B-it-Power:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf librepowerai/Gemma-3-4B-it-Power:Q4_K_M

Use Docker

docker model run hf.co/librepowerai/Gemma-3-4B-it-Power:Q4_K_M

LM Studio
Jan
Ollama
How to use librepowerai/Gemma-3-4B-it-Power with Ollama:
```
ollama run hf.co/librepowerai/Gemma-3-4B-it-Power:Q4_K_M
```

Unsloth Studio

How to use librepowerai/Gemma-3-4B-it-Power 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 librepowerai/Gemma-3-4B-it-Power 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 librepowerai/Gemma-3-4B-it-Power to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for librepowerai/Gemma-3-4B-it-Power to start chatting

Atomic Chat new
Docker Model Runner
How to use librepowerai/Gemma-3-4B-it-Power with Docker Model Runner:
```
docker model run hf.co/librepowerai/Gemma-3-4B-it-Power:Q4_K_M
```

Lemonade

How to use librepowerai/Gemma-3-4B-it-Power with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull librepowerai/Gemma-3-4B-it-Power:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-3-4B-it-Power-Q4_K_M

List all available models

lemonade list

Gemma-3-4B-it — Q4_K_M for IBM Power (Linux ppc64le + AIX)

This is a modified (quantized, text-only) version of google/gemma-3-4b-it, packaged by LibrePower as Q4_K_M (Q6_K output head) GGUF for CPU inference on IBM Power (POWER9 VSX, POWER10/11 MMA-accelerated). No GPU required.

Gemma license. This model is governed by the Gemma Terms of Use and the Gemma Prohibited Use Policy, which apply to you as a downstream user. The weights have been modified (quantized to Q4_K_M, text-only, endianness-converted). NOT Apache-2.0 — unlike the rest of the LibrePower catalog.

Run it

Ubuntu / Debian ppc64le:

sudo apt install librepower-llama
lp-llama-models get gemma-3-4b      # or wget the LE file below
lp-llama-completion -m Gemma-3-4B-it-Q4_K_M.gguf -p "Hola!" -n 64 -t $(nproc)

IBM AIX 7.3 (big-endian):

dnf install llama-aix
wget https://huggingface.co/librepowerai/Gemma-3-4B-it-Power/resolve/main/Gemma-3-4B-it-Q4_K_M-be.gguf
lp-llama-completion -m Gemma-3-4B-it-Q4_K_M-be.gguf -p "Hola!" -n 64 -t $(nproc)

Files

Gemma-3-4B-it-Q4_K_M.gguf — little-endian (Ubuntu/Linux ppc64le)
Gemma-3-4B-it-Q4_K_M-be.gguf — big-endian (IBM AIX)

Good for

Multilingual chat and assistance (140+ languages), summarization, general instruction following. Text-only build (the original is multimodal).

Credits

Base model: Google Gemma (Gemma Terms of Use). Quantization & Power packaging: LibrePower.

Downloads last month: 45

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for librepowerai/Gemma-3-4B-it-Power

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

(466)

this model