NVIDIA Releases Groq 3 LPX for Agentic AI with 4x Faster Inference
NVIDIA Blog · rss · 2026-08-24
NVIDIA announced the production launch of NVIDIA Groq 3 LPX, an extension to the Vera Rubin NVL72 system designed for low-latency inference in the agentic era. In benchmarks running Gemma 4 31B, it delivered 3,400 tokens per second, 4x faster than the nearest alternative. SpaceXAI adopted NVIDIA Vera CPUs for agentic AI, while CoreWeave and Nebius deployed associated networking and acceleration tech.
More from Infra
- Jensen Huang joins BG2 podcast: does AI revenue justify capex, '27 bottlenecks — elonmusk · 2026-10-16
- Mistral's on-device infra rack revealed: DGX Spark, Mac Studio and more — gregmushen · 2026-10-16
- NVIDIA and Sweden's Wallenberg launch Sferical One, a shared AI supercomputer — nvidia · 2026-10-16
- Next infra frontier: self-evolving systems that adapt and self-verify — _shreya_s · 2026-10-16
- Xiaomi's MiMo RL dashboard reveals $3.47M spent on just 30 training steps — bycloud · 2026-10-16
- Cerebras pushes disaggregated inference: heterogeneous prefill pools feeding wafer-scale decode — ai · 2026-10-16