Instructions to use gghfez/gemma-3-12b-novision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gghfez/gemma-3-12b-novision with Transformers:

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

pipe = pipeline("text-generation", model="gghfez/gemma-3-12b-novision")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gghfez/gemma-3-12b-novision")
model = AutoModelForCausalLM.from_pretrained("gghfez/gemma-3-12b-novision")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use gghfez/gemma-3-12b-novision with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gghfez/gemma-3-12b-novision"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gghfez/gemma-3-12b-novision",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gghfez/gemma-3-12b-novision

SGLang

How to use gghfez/gemma-3-12b-novision 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 "gghfez/gemma-3-12b-novision" \
    --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": "gghfez/gemma-3-12b-novision",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "gghfez/gemma-3-12b-novision" \
        --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": "gghfez/gemma-3-12b-novision",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gghfez/gemma-3-12b-novision with Docker Model Runner:
```
docker model run hf.co/gghfez/gemma-3-12b-novision
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Gemma-3-12b Text-Only

This model is a text-only version of google/gemma-3-12b-it, converted from the multimodal Gemma3ForConditionalGeneration architecture to the text-only Gemma3ForCausalLM architecture.

Model Description

Original Model: The original Gemma-3-12b-it is a multimodal model released by Google that can process both text and images
This Version: This version has been modified to use the same architecture as the text-only 1b model, with the vision components removed
Parameters: 4 billion parameters
Conversion Process: Vision-related components were stripped while maintaining the text generation capabilities

Usage

You can load and use this model the same way you would use the text-only google/gemma-3-1b-it version:

from transformers import AutoTokenizer, BitsAndBytesConfig, Gemma3ForCausalLM
import torch

model_id = "gghfez/gemma-3-12b-novision"

quantization_config = BitsAndBytesConfig(load_in_8bit=True)

model = Gemma3ForCausalLM.from_pretrained(
    model_id, quantization_config=quantization_config
).eval()

tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [
    [
        {
            "role": "system",
            "content": [{"type": "text", "text": "You are a helpful assistant."},]
        },
        {
            "role": "user",
            "content": [{"type": "text", "text": "Write a poem on Hugging Face, the company"},]
        },
    ],
]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device).to(torch.bfloat16)


with torch.inference_mode():
    outputs = model.generate(**inputs, max_new_tokens=64)

outputs = tokenizer.batch_decode(outputs)