Serving 2 Million Models Without Melting: Scaling the Hugging Face Hub

Official Schedule Context

Hugging Face hosts over 2 million public models, 500,000+ datasets, and serves 13 million users

across 50,000+ organizations, including over 30% of the Fortune 500. That growth didn't come with a

manual.In this talk, we'll pull back the curtain on the infrastructure decisions that kept the Hub

fast and reliable as traffic grew by orders of magnitude. We'll dive into why we chose MongoDB Atlas

as our core data layer, how its document model maps naturally to the messy reality of ML model

metadata, and what it took to keep p99 latency low when every request hits a catalog of millions.

We'll also cover the trade-offs we faced, the things that broke along the way, and what "lean

operations" actually means when your platform serves a third of the Fortune 500. Expect real

architecture decisions, real numbers, and lessons you can take back to your own stack.

No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

Pending transcript synthesis when an official recording or confirmed matching video is available.