Instructions to use tensorblock/shieldgemma-9b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/shieldgemma-9b-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="tensorblock/shieldgemma-9b-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/shieldgemma-9b-GGUF", dtype="auto")

llama-cpp-python

How to use tensorblock/shieldgemma-9b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/shieldgemma-9b-GGUF",
	filename="shieldgemma-9b-Q2_K.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 tensorblock/shieldgemma-9b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/shieldgemma-9b-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/shieldgemma-9b-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/shieldgemma-9b-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/shieldgemma-9b-GGUF:Q2_K

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 tensorblock/shieldgemma-9b-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/shieldgemma-9b-GGUF:Q2_K

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 tensorblock/shieldgemma-9b-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/shieldgemma-9b-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/shieldgemma-9b-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/shieldgemma-9b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/shieldgemma-9b-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": "tensorblock/shieldgemma-9b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tensorblock/shieldgemma-9b-GGUF:Q2_K

SGLang

How to use tensorblock/shieldgemma-9b-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "tensorblock/shieldgemma-9b-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/shieldgemma-9b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "tensorblock/shieldgemma-9b-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/shieldgemma-9b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use tensorblock/shieldgemma-9b-GGUF with Ollama:
```
ollama run hf.co/tensorblock/shieldgemma-9b-GGUF:Q2_K
```

Unsloth Studio new

How to use tensorblock/shieldgemma-9b-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 tensorblock/shieldgemma-9b-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 tensorblock/shieldgemma-9b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/shieldgemma-9b-GGUF to start chatting

Docker Model Runner
How to use tensorblock/shieldgemma-9b-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/shieldgemma-9b-GGUF:Q2_K
```

Lemonade

How to use tensorblock/shieldgemma-9b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/shieldgemma-9b-GGUF:Q2_K

Run and chat with the model

lemonade run user.shieldgemma-9b-GGUF-Q2_K

List all available models

lemonade list

google/shieldgemma-9b - GGUF

This repo contains GGUF format model files for google/shieldgemma-9b.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Our projects

Forge

An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio

A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template

<bos>You are a policy expert trying to help determine whether a user prompt is in violation of the defined safety policies.

<start_of_turn>
Human Question: {prompt}
<end_of_turn>

Our safety principle is defined in the below:

* {system_prompt}

===

Does the human question violate the above principle? Your answer must start with 'Yes' or 'No'. And then walk through step by step to be sure we answer correctly.

Model file specification

Filename	Quant type	File Size	Description
shieldgemma-9b-Q2_K.gguf	Q2_K	3.805 GB	smallest, significant quality loss - not recommended for most purposes
shieldgemma-9b-Q3_K_S.gguf	Q3_K_S	4.338 GB	very small, high quality loss
shieldgemma-9b-Q3_K_M.gguf	Q3_K_M	4.762 GB	very small, high quality loss
shieldgemma-9b-Q3_K_L.gguf	Q3_K_L	5.132 GB	small, substantial quality loss
shieldgemma-9b-Q4_0.gguf	Q4_0	5.443 GB	legacy; small, very high quality loss - prefer using Q3_K_M
shieldgemma-9b-Q4_K_S.gguf	Q4_K_S	5.479 GB	small, greater quality loss
shieldgemma-9b-Q4_K_M.gguf	Q4_K_M	5.761 GB	medium, balanced quality - recommended
shieldgemma-9b-Q5_0.gguf	Q5_0	6.484 GB	legacy; medium, balanced quality - prefer using Q4_K_M
shieldgemma-9b-Q5_K_S.gguf	Q5_K_S	6.484 GB	large, low quality loss - recommended
shieldgemma-9b-Q5_K_M.gguf	Q5_K_M	6.647 GB	large, very low quality loss - recommended
shieldgemma-9b-Q6_K.gguf	Q6_K	7.589 GB	very large, extremely low quality loss
shieldgemma-9b-Q8_0.gguf	Q8_0	9.827 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/shieldgemma-9b-GGUF --include "shieldgemma-9b-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/shieldgemma-9b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'

Downloads last month: 22

GGUF

Model size

9B params

Architecture

gemma2

Hardware compatibility

2-bit

Model tree for tensorblock/shieldgemma-9b-GGUF

Base model

google/shieldgemma-9b

Quantized

(10)

this model