AITom's Hardwareabout 1 hour ago
Nvidia unveils Groq 3 LPX architecture at Hot Chips 2026
6 min read
Nvidia's Igor Arsovski presented the Groq 3 LPX rack architecture at Hot Chips 2026. Artificial Analysis benchmarked it at 3,431 output tokens per second on a 100K-context Gemma 4 31B reasoning workload. The LP30-based rack is already in production.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyNvidia
Summary by ByteBrief
