Webinar: Kimi K3 on Fireworks

K3 is here. The world's first open frontier model in the 3-trillion-parameter class. Come see how to run it, train it, and put it to work, on Fireworks.

Speakers

James Reed | Co-Founder at Fireworks

Previously PyTorch compiler at Meta

Sinan Ozdemir | Head of AI Developer Education at Fireworks

Previously Author of 10+ books on LLMs and agentic AI, founder of Kylie.ai (early agentic AI, YC-backed, acquired 2019), AI Lecturer/Author for Pearson + O'Reilly, and your friendly neighborhood ML engineer.

K3 overview (in case you missed it)

Moonshot AI just released Kimi K3, a 2.8-trillion-parameter open-weights model with native vision and a 1M-token context window. It rivals the top closed frontier models on coding, agentic, and reasoning tasks while being a fraction of the cost. We'll give you the tour: what K3 is, where it lands against other frontier models, and why an open model at this scale changes the calculus for what you build and where you run it.

How to use K3 on Fireworks inference

K3 went live on Fireworks Day 0 for both inference and training. It’s US-hosted, with zero-data-retention options, and you have no GPUs to manage. We'll walk through serverless pay-by-token access and the deployment paths available as your workload grows, so you can go from "curious" to "in production" ASAP.

Post-Training K3 on the Fireworks Training API

Live, runnable examples against the Fireworks Training API. Watch as we post-train an agent on top of K3 using Fireworks’ new serverless training API. Full examples will be available on GitHub.

Open Q&A

Ask us anything about K3, Fireworks, fine-tuning, or just AI in general.