Small Language Models (SLMs) for Production Workflows
Registration
Past Event
About Event
Bigger models aren’t always better for production.
In this office hour, we’ll break down how Small Language Models (SLMs) can power real-world workflows with lower latency, lower cost, and higher reliability than large general-purpose models, when aligned to the right tasks.
We’ll cover:
When SLMs outperform large models in production
How to route, specialize, and evaluate models by task
Real examples of cutting inference costs without sacrificing performance
Bring your use cases and questions, this is a practical, hands-on discussion for teams building AI that actually ships.
Check out our leaderboard