Serving 2 Million Models Without Melting: Scaling the Hugging Face Hub
Conference Context
- Date/time: 2026-06-29 · 1:30pm-1:50pm
- Track/room: AI Architects: Show my Workflow · Leadership 2
- Speaker(s): Arek Borucki
- Session type/status: session · confirmed
- Track: AI Architects: Show my Workflow
- Room: Leadership 2
- Session type: session
- Status: confirmed
Session Description
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.
Media Evidence
No related AI Engineer channel video found yet.
Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.
Media Signals
No linked video, transcript, or slide source has been attached yet.
Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.
Transcript Status
No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.
People
Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.
Synthesis
Synthesized Breakdown
Serving 2 Million Models Without Melting: Scaling the Hugging Face Hub ## Conference Context - Date/time: 2026-06-29 · 1:30pm-1:50pm - Track/room: AI Architects: Show my Workflow · Leadership 2 - Speaker(s): Arek Borucki - Session type/status: session · confirmed - Track: AI Architects: Show my Workflow - Room: Leadership 2 - Session type: session - Status: confirmed ## Session Description 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.
Speaker And Company Context
- Arek Borucki — Machine Learning Platform & Database Engineer at Hugging Face.
Topics Covered
- Topic links are pending transcript-backed classification.
Derived Links And Source Material
Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.
Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.