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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use backpack-run/gemma-3-4b-it-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 backpack-run/gemma-3-4b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf backpack-run/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 serve -hf backpack-run/gemma-3-4b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf backpack-run/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 backpack-run/gemma-3-4b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf backpack-run/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 backpack-run/gemma-3-4b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf backpack-run/gemma-3-4b-it-GGUF:Q4_K_M

Use Docker

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

LM Studio
Jan

vLLM

How to use backpack-run/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 "backpack-run/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": "backpack-run/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/backpack-run/gemma-3-4b-it-GGUF:Q4_K_M

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

Unsloth Studio

How to use backpack-run/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 backpack-run/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 backpack-run/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 backpack-run/gemma-3-4b-it-GGUF to start chatting

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

Lemonade

How to use backpack-run/gemma-3-4b-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull backpack-run/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

Atomic Chat

Access Gemma GGUF on Hugging Face

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

By requesting access, you acknowledge that these model derivatives are subject to the Gemma Terms of Use and the incorporated Gemma Prohibited Use Policy.

gemma-3-4b-it — Backpack GGUF

🎒 Backpack Verified

GGUF quantizations of google/gemma-3-4b-it, tested for llama.cpp-compatible image-and-text inference and packaged for Backpack.

Model

Property	Value
Original model	`google/gemma-3-4b-it`
Original publisher	google
Upstream revision	`093f9f388b31de276ce2de164bdc2081324b9767`
Architecture	Gemma3ForConditionalGeneration
Parameters	4,300,079,472
Context length	Not declared
Input modalities	text, image
Output modalities	text
License	gemma

Available packages

Quantization	Size	Approx. RAM	Recommended for
Q4_K_M	2.3 GiB	5.21 GB	Most users
Q5_K_M	2.6 GiB	5.67 GB	Higher quality
Q8_0	3.8 GiB	7.43 GB	Plenty of memory

Memory values are estimates, not guarantees. Runtime configuration and context length change actual use.

Multimodal projector

File	Precision	Size
`gemma-3-4b-it-mmproj-F16.gguf`	F16	811.8 MiB

The projector is required for image input and must be used with one of the language-model GGUF files above.

Backpack recommendation

Recommended: Q4_K_M. It usually offers a practical quality, size, and speed balance for local inference.

Run with llama.cpp

Using the llama.cpp revision recorded below:

llama-mtmd-cli --model gemma-3-4b-it-Q4_K_M.gguf --mmproj gemma-3-4b-it-mmproj-F16.gguf --image image.jpg --prompt "Describe this image."

Run with Backpack

These artifacts and backpack-model.yaml are prepared for the Backpack AI workspace.

Validation

Package	Integrity	Load	Inference	Tokenizer
Q4_K_M	passed	passed	passed	passed
Q5_K_M	passed	passed	passed	passed
Q8_0	passed	passed	passed	passed

Packaged: 2026-08-22T18:52:28.790344+00:00
llama.cpp revision: de699957b92f490efebad149665b0dccf127eaff
SHA-256 checksums: see checksums.sha256
gemma-3-4b-it-Q4_K_M.gguf: 828f5cbc6ab8323700eb710f98a09cca97095e159e3ad867b50e60529693b80b
gemma-3-4b-it-Q5_K_M.gguf: 85e38a4e3369c392403a3fecb4e088bf1872724cca2b9e6d962b969186dcda47
gemma-3-4b-it-Q8_0.gguf: 3ec9257d99eb01dd5c4fd8ee7237498d2d802e2ad12e19b11f0caa64e97612ce
gemma-3-4b-it-mmproj-F16.gguf: 1a38560c740c76e3ff2f702b9b3056296a1d22801ec14cd04f9fac6160040ef9

Provenance

The source model was resolved to immutable revision 093f9f388b31de276ce2de164bdc2081324b9767. It was converted with llama.cpp's convert_hf_to_gguf.py, including its multimodal projector, and quantized with llama-quantize; the exact tested revision is recorded above and in backpack-model.yaml.

License and attribution

Upstream declares gemma. Review the upstream model card and comply with all applicable terms.

This repository and every included GGUF are Model Derivatives subject to the Gemma Terms of Use, including its Section 3.2 use restrictions and incorporated Gemma Prohibited Use Policy. The complete agreement is included as LICENSE, and the required distribution notice is included as NOTICE.

Modification notice: Backpack converted the immutable upstream SafeTensors weights to GGUF, extracted the multimodal projector, and quantized the language-model GGUF files. Google did not produce or endorse these modified files.

Backpack does not claim ownership of the original model. These artifacts are packaged and quantized distributions of the upstream model.

Disclaimer

Quantization can alter output quality. Memory estimates vary with runtime configuration, context length, and hardware.

Downloads last month: -

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

4-bit

5-bit

8-bit

Model tree for backpack-run/gemma-3-4b-it-GGUF

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

(482)

this model