Build Kaggle Multi-GPU LLM API

I need one self-contained Kaggle notebook (.ipynb) that spins up a free, publicly reachable LLM inference API. The end goal is strictly research purposes, and the responses the service returns will be used for code generation experiments... (Budget: $5 - $6 USD, Jobs: API Development, Cloud Computing, CUDA, Data Science, Deep Learning, Model Deployment, Python, Research)