Instructions to use almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext with Transformers:

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

pipe = pipeline("image-text-to-text", model="almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext")
model = AutoModelForMultimodalLM.from_pretrained("almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext",
		"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/almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext

SGLang

How to use almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext 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 "almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext" \
    --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": "almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext",
		"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 "almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext" \
        --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": "almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext with Docker Model Runner:
```
docker model run hf.co/almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext
```

Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext

AWQ INT4 weights for google/gemma-4-12B-it, prepared for lower VRAM use while keeping the base model practical for text, image, audio, structured output, and long-context experiments.

Quantization

Method: AWQ
Weight format: INT4
Compute scheme: W4A16
Calibration samples: 128
Max calibration length: 4096 tokens
Calibration style: document QA, OCR-style text, structured JSON output, coding prompts, table and chart descriptions, transcript-style prompts, and long-context retrieval prompts
Tooling: LLM Compressor 0.12.0, Transformers 5.10.1, PyTorch 2.11.0+cu128
GPU used: NVIDIA A100-SXM4-80GB

Local Check

A short generation check was run after saving the weights.

Test prompt: return a JSON object with status: ok
Result: passed
Peak VRAM during local load test: 22.98 GB

Notes

These weights are intended for practical inference tests with lower memory use than the original precision. Quantization can affect exact wording, numeric precision, and long-context recall. Full 256K context behavior should only be assumed after testing in your own setup.

Downloads last month: 105

Safetensors

Model size

12B params

Tensor type

I64

I32

BF16

Model tree for almernzh/Gemma-4-12B-it-AWQ-INT4-Multimodal-LongContext

Base model

google/gemma-4-12B

Finetuned

google/gemma-4-12B-it

Quantized

(302)

this model