Instructions to use google/gemma-3-4b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-3-4b-it with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="google/gemma-3-4b-it")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("google/gemma-3-4b-it", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use google/gemma-3-4b-it with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "google/gemma-3-4b-it" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "google/gemma-3-4b-it", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/google/gemma-3-4b-it
- SGLang
How to use google/gemma-3-4b-it 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 "google/gemma-3-4b-it" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "google/gemma-3-4b-it", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "google/gemma-3-4b-it" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "google/gemma-3-4b-it", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use google/gemma-3-4b-it with Docker Model Runner:
docker model run hf.co/google/gemma-3-4b-it
Missing values in 4B, 12B config.json
The 4B config is missing some values that are included in the 12B and 27B configs. The 4B and 12B configs are missing some values that are included in the 27B config.
Please ensure that the values specified in the config files are always present for differently sized models that use the same architecture. Otherwise developers have to waste hours of work on debugging and adding fallbacks.
i got same issue
Hi @depasquale ,
Welcome to Google Gemma family of open models, thanks for notifying us on the configuration discrepancy across the different variants. I have escalated your concern to internal team. Thanks for you support and understanding.
Thanks.