Cloud Run lets you attach GPUs to deploy open models and serve AI
inference. You can train, fine-tune, and run models with
accelerated performance.

If you are new to AI concepts, see
[GPUs for AI](https://cloud.google.com/discover/gpu-for-ai). To learn more
about configuration options, see GPU support for
[services](https://docs.cloud.google.com/run/docs/configuring/services/gpu.md.txt),
[jobs](https://docs.cloud.google.com/run/docs/configuring/jobs/gpu.md.txt), and
[worker pools](https://docs.cloud.google.com/run/docs/configuring/workerpools/gpu.md.txt).

## Tutorials for services

- [Run Gemma on Cloud Run](https://docs.cloud.google.com/run/docs/run-gemma-on-cloud-run.md.txt)
- [Run LLM inference on Cloud Run GPUs with Gemma and Ollama](https://docs.cloud.google.com/run/docs/tutorials/gpu-gemma-with-ollama.md.txt)
- [Run OpenCV on Cloud Run with GPU acceleration](https://docs.cloud.google.com/run/docs/tutorials/gpu-opencv-with-cuda.md.txt)
- [Run LLM inference on Cloud Run GPUs with Hugging Face Transformers.js](https://docs.cloud.google.com/run/docs/tutorials/gpu-gemma2-with-transformers-js.md.txt)

## Tutorials for jobs

- [Fine tune LLMs using GPUs with Cloud Run jobs](https://docs.cloud.google.com/run/docs/tutorials/gpu-finetune-with-jobs.md.txt)
- [Run batch inference using GPUs on Cloud Run jobs](https://docs.cloud.google.com/run/docs/tutorials/jobs-gpu-batch-inference.md.txt)
- [GPU-accelerated video transcoding with FFmpeg on Cloud Run jobs](https://docs.cloud.google.com/run/docs/tutorials/video-encoding.md.txt)