gemma-4-E4B-it-int8-ov

• Model creator: google
• Original model: gemma-4-E4B-it

[!WARNING] EXPERIMENTAL MODEL This model has not been fully validated with OpenVINO and is using a custom branch of optimum-intel. It may be fully supported and validated in the future.

Description

This is gemma-4-E4B-it model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT8 by NNCF.

Quantization Parameters

Weight compression was performed using nncf.compress_weights with the following parameters:

• mode: INT8_ASYM
• group_size: -1

For more information on quantization, check the OpenVINO model optimization guide.

Compatibility

The provided OpenVINO™ IR model is compatible with:

• OpenVINO version 2026.4.0 and higher
• Optimum Intel 2.2.0 and higher

Running Model Inference with Optimum Intel

1. Install packages required for using Optimum Intel:

pip install "git+https://github.com/huggingface/optimum-intel.git" --extra-index-url https://download.pytorch.org/whl/cpu
pip install transformers==5.5.4
pip install torchvision Pillow --extra-index-url https://download.pytorch.org/whl/cpu

2. Run model inference:

from optimum.intel.openvino import OVModelForVisualCausalLM
from transformers import AutoProcessor
from PIL import Image
import requests

model_id = "OpenVINO/gemma-4-E4B-it-int8-ov"
processor = AutoProcessor.from_pretrained(model_id)
model = OVModelForVisualCausalLM.from_pretrained(model_id)

url = "https://github.com/openvinotoolkit/openvino_notebooks/assets/29454499/d5fbbd1a-d484-415c-88cb-9986625b7b11"
image = Image.open(requests.get(url, stream=True).raw)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": image},
            {"type": "text", "text": "What is unusual in this picture?"},
        ],
    }
]

text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=text, images=[image], return_tensors="pt")
input_len = inputs["input_ids"].shape[-1]

output = model.generate(**inputs, do_sample=False, max_new_tokens=100)
response = processor.decode(output[0][input_len:], skip_special_tokens=True)
print(response)

You can find more detailed usage examples in OpenVINO Notebooks:

• Gemma 4

Running Model with OpenAI client and OpenVINO Model Server

1a. Deploy model on Windows using binary package:

curl -o ovms.zip https://storage.openvinotoolkit.org/repositories/openvino_model_server/packages/weekly/latest/ovms_windows.zip
tar -xf ovms.zip
set OVMS_MEDIA_URL_ALLOW_REDIRECTS=1
ovms.exe --rest_port 8000 --source_model OpenVINO/gemma-4-E4B-it-int8-ov --model_repository_path C:\models --allowed_media_domains all

1b. Deploy model in a Docker container:

export GPU_ARGS=$(if ls /dev/dri/render* >/dev/null 2>&1; then echo "--device /dev/dri --group-add $(stat -c '%g' /dev/dri/render* | head -n1)"; fi)
docker run -d ${GPU_ARGS} -e "OVMS_MEDIA_URL_ALLOW_REDIRECTS=1" -u $(id -u):$(id -g) --rm -p 8000:8000 -v ${HOME}/models:/models:rw openvino/model_server:weekly \
--rest_port 8000 --model_repository_path /models --source_model OpenVINO/gemma-4-E4B-it-int8-ov --allowed_media_domains all

2. Install the client library:

pip install openai

3. Run the client:

from openai import OpenAI

client = OpenAI(
  base_url="http://localhost:8000/v1",
  api_key="unused"
)

image_url = "https://github.com/openvinotoolkit/openvino_notebooks/assets/29454499/d5fbbd1a-d484-415c-88cb-9986625b7b11"

stream = client.chat.completions.create(
    model="OpenVINO/gemma-4-E4B-it-int8-ov",
    messages=[
    {
        "role": "user",
        "content": [
            {"type": "image_url", "image_url": {"url": image_url}},
            {"type": "text", "text": "What is unusual in this picture?"},
        ],
    }
    ],
    stream=True,
    extra_body={"chat_template_kwargs": {"enable_thinking": "true"}},
    tools=[],
)

printing_reasoning_started = False
printing_content_started = False
for chunk in stream:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta

    content = getattr(delta, "content", None)
    reasoning = getattr(delta, "reasoning_content", None)

    if content:
        if not printing_content_started:
            printing_content_started = True
            print("\ncontent:\n", end="", flush=True)
        print(content, end="", flush=True)
    if reasoning:
        if not printing_reasoning_started:
            printing_reasoning_started = True
            print("reasoning_content:\n", end="", flush=True)
        print(reasoning, end="", flush=True)

Limitations

Check the original model card for limitations.

Legal information

The original model is distributed under Apache License Version 2.0 license. More details can be found in gemma-4-E4B-it.

Disclaimer

Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See Intel's Global Human Rights Principles. Intel's products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.