Instructions to use abhishekchohan/gemma-3-27b-it-quantized-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abhishekchohan/gemma-3-27b-it-quantized-W4A16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="abhishekchohan/gemma-3-27b-it-quantized-W4A16")
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("abhishekchohan/gemma-3-27b-it-quantized-W4A16")
model = AutoModelForImageTextToText.from_pretrained("abhishekchohan/gemma-3-27b-it-quantized-W4A16")
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

vLLM

How to use abhishekchohan/gemma-3-27b-it-quantized-W4A16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abhishekchohan/gemma-3-27b-it-quantized-W4A16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abhishekchohan/gemma-3-27b-it-quantized-W4A16",
		"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/abhishekchohan/gemma-3-27b-it-quantized-W4A16

SGLang

How to use abhishekchohan/gemma-3-27b-it-quantized-W4A16 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 "abhishekchohan/gemma-3-27b-it-quantized-W4A16" \
    --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": "abhishekchohan/gemma-3-27b-it-quantized-W4A16",
		"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 "abhishekchohan/gemma-3-27b-it-quantized-W4A16" \
        --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": "abhishekchohan/gemma-3-27b-it-quantized-W4A16",
		"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 abhishekchohan/gemma-3-27b-it-quantized-W4A16 with Docker Model Runner:
```
docker model run hf.co/abhishekchohan/gemma-3-27b-it-quantized-W4A16
```

Gemma 3 Quantized Models

This repository contains W4A16 quantized versions of Google's Gemma 3 instruction-tuned models, making them more accessible for deployment on consumer hardware while maintaining good performance.

Models

abhishekchohan/gemma-3-27b-it-quantized-W4A16
abhishekchohan/gemma-3-12b-it-quantized-W4A16
abhishekchohan/gemma-3-4b-it-quantized-W4A16

Repository Structure

gemma-3-{size}-it-quantized-W4A16/
├── README.md
├── templates/
│   └── chat_template.jinja
├── tools/
│   └── tool_parser.py
└── [model files]

Quantization Details

These models use W4A16 quantization via LLM Compressor:

Weights quantized to 4-bit precision
Activations use 16-bit precision
Significantly reduced memory requirements

Usage with vLLM

vllm serve abhishekchohan/gemma-3-{size}-it-quantized-W4A16 --chat-template templates/chat_template.jinja --enable-auto-tool-choice --tool-call-parser gemma --tool-parser-plugin tools/tool_parser.py

License

These models are subject to the Gemma license. Users must acknowledge and accept the license terms before using the models.

Citation

@article{gemma_2025,
    title={Gemma 3},
    url={https://goo.gle/Gemma3Report},
    publisher={Kaggle},
    author={Gemma Team},
    year={2025}
}

Downloads last month: 22

Safetensors

Model size

28B params

Tensor type

I64

I32

BF16

Model tree for abhishekchohan/gemma-3-27b-it-quantized-W4A16

Base model

google/gemma-3-27b-pt

Finetuned

google/gemma-3-27b-it

Quantized

(134)

this model

Collection including abhishekchohan/gemma-3-27b-it-quantized-W4A16

Gemma 3 Quantized Collection

Collection

3 items • Updated Mar 17, 2025 • 1