Instructions to use second-state/gemma-3-4b-it-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use second-state/gemma-3-4b-it-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="second-state/gemma-3-4b-it-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("second-state/gemma-3-4b-it-GGUF")
model = AutoModelForImageTextToText.from_pretrained("second-state/gemma-3-4b-it-GGUF")

llama-cpp-python

How to use second-state/gemma-3-4b-it-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="second-state/gemma-3-4b-it-GGUF",
	filename="gemma-3-4b-it-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use second-state/gemma-3-4b-it-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf second-state/gemma-3-4b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf second-state/gemma-3-4b-it-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 second-state/gemma-3-4b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf second-state/gemma-3-4b-it-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 second-state/gemma-3-4b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf second-state/gemma-3-4b-it-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 second-state/gemma-3-4b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf second-state/gemma-3-4b-it-GGUF:Q4_K_M

Use Docker

docker model run hf.co/second-state/gemma-3-4b-it-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use second-state/gemma-3-4b-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "second-state/gemma-3-4b-it-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": "second-state/gemma-3-4b-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/second-state/gemma-3-4b-it-GGUF:Q4_K_M

SGLang

How to use second-state/gemma-3-4b-it-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 "second-state/gemma-3-4b-it-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": "second-state/gemma-3-4b-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "second-state/gemma-3-4b-it-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": "second-state/gemma-3-4b-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use second-state/gemma-3-4b-it-GGUF with Ollama:
```
ollama run hf.co/second-state/gemma-3-4b-it-GGUF:Q4_K_M
```

Unsloth Studio new

How to use second-state/gemma-3-4b-it-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 second-state/gemma-3-4b-it-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 second-state/gemma-3-4b-it-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for second-state/gemma-3-4b-it-GGUF to start chatting

Docker Model Runner
How to use second-state/gemma-3-4b-it-GGUF with Docker Model Runner:
```
docker model run hf.co/second-state/gemma-3-4b-it-GGUF:Q4_K_M
```

Lemonade

How to use second-state/gemma-3-4b-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull second-state/gemma-3-4b-it-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-3-4b-it-GGUF-Q4_K_M

List all available models

lemonade list

Gemma-3-4b-it-GGUF

Original Model

google/gemma-3-4b-it

Run with LlamaEdge

LlamaEdge version: v0.18.5 and above

Prompt template

Prompt type: gemma-3

Prompt string

<bos><start_of_turn>user
{user_message}<end_of_turn>
<start_of_turn>model
{model_message}<end_of_turn>model

Context size: 128000

Run as LlamaEdge service

Chat

wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-3-4b-it-Q5_K_M.gguf \
  llama-api-server.wasm \
  --prompt-template gemma-3 \
  --ctx-size 128000 \
  --model-name gemma-3-4b

Images

Note that input images are required to be normalized to 896 x 896 resolution and encoded to 256 tokens each

wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-3-4b-it-Q5_K_M.gguf \
  llama-api-server.wasm \
  --prompt-template gemma-3 \
  --llava-mmproj gemma-3-4b-it-mmproj-f16.gguf \
  --ctx-size 128000 \
  --model-name gemma-3-4b

Run as LlamaEdge command app

wasmedge --dir .:. \
  --nn-preload default:GGML:AUTO:gemma-3-4b-it-Q5_K_M.gguf \
  llama-chat.wasm \
  --prompt-template gemma-3 \
  --ctx-size 128000

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
gemma-3-4b-it-Q2_K.gguf	Q2_K	2	1.73 GB	smallest, significant quality loss - not recommended for most purposes
gemma-3-4b-it-Q3_K_L.gguf	Q3_K_L	3	2.24 GB	small, substantial quality loss
gemma-3-4b-it-Q3_K_M.gguf	Q3_K_M	3	2.10 GB	very small, high quality loss
gemma-3-4b-it-Q3_K_S.gguf	Q3_K_S	3	1.94 GB	very small, high quality loss
gemma-3-4b-it-Q4_0.gguf	Q4_0	4	2.36 GB	legacy; small, very high quality loss - prefer using Q3_K_M
gemma-3-4b-it-Q4_K_M.gguf	Q4_K_M	4	2.49 GB	medium, balanced quality - recommended
gemma-3-4b-it-Q4_K_S.gguf	Q4_K_S	4	2.38 GB	small, greater quality loss
gemma-3-4b-it-Q5_0.gguf	Q5_0	5	2.76 GB	legacy; medium, balanced quality - prefer using Q4_K_M
gemma-3-4b-it-Q5_K_M.gguf	Q5_K_M	5	2.83 GB	large, very low quality loss - recommended
gemma-3-4b-it-Q5_K_S.gguf	Q5_K_S	5	2.76 GB	large, low quality loss - recommended
gemma-3-4b-it-Q6_K.gguf	Q6_K	6	3.19 GB	very large, extremely low quality loss
gemma-3-4b-it-Q8_0.gguf	Q8_0	8	4.13 GB	very large, extremely low quality loss - not recommended
gemma-3-4b-it-f16.gguf	f16	16	7.77 GB
gemma-3-4b-it-mmproj-f16.gguf	f16	16	851 MB

Quantized with llama.cpp b4875

Downloads last month: 1,172

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for second-state/gemma-3-4b-it-GGUF

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

(462)

this model

Collection including second-state/gemma-3-4b-it-GGUF

Gemma-3-it GGUF Models

Collection

LlamaEdge compatible quants for Gemma-3-it models. • 4 items • Updated Mar 12, 2025