Instructions to use google/gemma-3-1b-pt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-3-1b-pt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="google/gemma-3-1b-pt")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("google/gemma-3-1b-pt") model = AutoModelForCausalLM.from_pretrained("google/gemma-3-1b-pt") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use google/gemma-3-1b-pt with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "google/gemma-3-1b-pt" # 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-3-1b-pt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/google/gemma-3-1b-pt
- SGLang
How to use google/gemma-3-1b-pt 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-3-1b-pt" \ --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-3-1b-pt", "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-3-1b-pt" \ --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-3-1b-pt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use google/gemma-3-1b-pt with Docker Model Runner:
docker model run hf.co/google/gemma-3-1b-pt
Request: DOI
Hi @pari-5461 ,
Welcome to Google's Gemma models, thanks for reaching out to us. I'm glad for your interest in the Gemma models.
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-3-1b-pt 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.
