You can fine tune a [Gemma 3 model](https://ai.google.dev/gemma/docs/core/model_card_3) on a Cloud Run job, then
serve the fine tuned model on a Cloud Run service using [vLLM](https://github.com/vllm-project/vllm).

See a step-by-step instructional codelab at [How to fine tune a model using Cloud Run jobs](https://codelabs.developers.google.com/codelabs/cloud-run/how-to-fine-tune-model-cloud-run-jobs#0).