Small Is the New Big: ship faster and cheaper with small models

​Small Is the New Big

​The industry keeps telling you that you need the biggest, newest frontier model. For most real workloads, that's a tax you're paying on cost and latency for capability you never use. This session makes the case for the other direction: a smaller, distilled model — tuned to your specific task and running on your own infra — that answers faster, costs a fraction, and keeps your data in your account.

​What to expect

​Self hosting the open-weight models on EKS.

​Who it's for

​Developers and technical founders running (or about to run) AI in production who care about cost and latency, not just demos.

​What you'll leave with

​A simple framework to decide model size per workload, a back-of-envelope cost model for your own numbers, and a clear picture of the path to faster, cheaper, private inference.

​This event is part of Basecamp, a community-powered tech week in Bengaluru bringing founders, builders, and operators together. Basecamp is free for the community and powered by the community.