Ultra-Fast Inference & Open-Weight Models
Hosted by FriendliAI + MiniMax
Register with organizer
What to look forward to
During Ignite week, FriendliAI will host an evening discussion on ultra-fast inference, open-weight models, serving infrastructure, and the cost and latency tradeoffs of production-scale AI. Short presentations from Victor Su-Ortiz of MiniMax, Salman Quazi of Reflection AI, and Yunmo Koo of FriendliAI will be followed by networking with builders, founders, and engineers.
Inside the event
An evening with FriendliAI during Ignite week!
In town for Ignite? Come close out the day at our office, just one block from Moscone Center, for a casual evening discussing ultra-fast inference and open-weight models.
Open-weight models like MiniMax M3 and Reflection AI's Beam land in more production workloads every month. The quality gaps have narrowed significantly between open and closed models, at a fraction of the cost. What separates a prototype from production scale is serving: how fast the tokens flow, and how much you pay for them.
What to expect
- Let's talk about the AI stack. Latency and throughput numbers, serving infrastructure, cost tradeoffs vs. closed models, and how it all holds up under agentic workloads.
- Meet and network with other professional builders, founders, and engineers. Some in town for Ignite, some locals, everyone trading notes on what they're exploring.
- Food and drinks are on us, all evening. Make sure you're registered, but no conference badge required.
Learn from the experts! Short presentations from these speakers
Capacity is limited. Doors open at 6pm PT. See you then!
San Francisco, CA
Venue listed by the organizer · San Francisco, CA. Confirm the final address before traveling.
Open in Google Maps ↗Details come from the event listing and the organizer page; registration is managed by the organizer.
Last checked: Nov 18, 2026. Confirm current availability before making plans.
Organizer page checked: Nov 18, 2026. Check registration for the latest details.