Instructions to use google/gemma-3-270m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-3-270m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="google/gemma-3-270m")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("google/gemma-3-270m") model = AutoModelForCausalLM.from_pretrained("google/gemma-3-270m") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use google/gemma-3-270m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "google/gemma-3-270m" # 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-3-270m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/google/gemma-3-270m
- SGLang
How to use google/gemma-3-270m 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-3-270m" \ --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-3-270m", "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-3-270m" \ --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-3-270m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use google/gemma-3-270m with Docker Model Runner:
docker model run hf.co/google/gemma-3-270m
Request: DOI
Hello Hugging Face Team,
I would like to request access to the model "google/gemma-3-270m" for personal research and fine-tuning purposes.
I plan to train a small LoRA for a custom conversational AI character.
My Hugging Face username: [YourUsername]
Thank you very much for your consideration.
Best regards,
Mohamad Zaitoun
Hi @jamalzeton80 ,
Thanks for reaching out to us!
The Gemma models are Gated models which means you need to request access directly from the model's Model card section on Hugging Face and use a valid access token to load the model locally. You can access the google/gemma-3-270m model using the granted access token or download the model weights for local use.
For generating access token in HuggingFace, could you please refer this documentation: https://huggingface.co/docs/transformers.js/en/guides/private
Thanks!