Instructions to use google/translategemma-4b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/translategemma-4b-it with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="google/translategemma-4b-it")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("google/translategemma-4b-it", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use google/translategemma-4b-it with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "google/translategemma-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/translategemma-4b-it", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/google/translategemma-4b-it
- SGLang
How to use google/translategemma-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/translategemma-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/translategemma-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/translategemma-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/translategemma-4b-it", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use google/translategemma-4b-it with Docker Model Runner:
docker model run hf.co/google/translategemma-4b-it
Are there plans to provide task or litertlm versions for the litt-literature community?
Hello
I would like to ask whether tasks will be provided through litert-community in the future, or whether web.litertlm or .litertlm versions will be available for use in the Web or Edge Gallery.
Hi @willopcbeta
We appreciate your interest in deploying Gemma via LiteRT on Web and Edge. While we cannot share specific plans for .litertlm versions at this time, I will pass on your feedback request to the relevant development team .
Thanks
I'm very looking forward to the day when it is officially released. Currently, the translation website I built using @mediapipe/tasks-genai delivers unexpectedly good translation speeds and quality on both computers and mobile devices (using models Gemma-3n and Gemma-3).
+1 on this request!
I'm trying to deploy TranslateGemma 4B in a native Android app using MediaPipe's LlmInference API. The web .task from litert-community doesn't work with the XNNPACK/GPU delegates on mobile.
Would love to see an official mobile-compatible .task bundle for Android/iOS deployment.
