# Nvidia says Groq 3 LPX enters production alongside Vera Rubin

_Monday, August 24, 2026 at 11:00 AM EDT · AI, Infrastructure · Breaking · Tier 1 — Major_

![Nvidia says Groq 3 LPX enters production alongside Vera Rubin — Primary](https://blogs.nvidia.com/wp-content/uploads/2026/08/HotChips_2026_MKT_KV_Rubin_Rack_Family_Front_comp_4k_V004-2-1-1680x945.png)

Nvidia said its Groq 3 LPX inference accelerator is in full production as an extension of its Vera Rubin NVL72 rack-scale system. The company said Nebius will be the first AI cloud to adopt LPX, while CoreWeave has deployed Spectrum-X Multiplane in production. Nvidia cited an Artificial Analysis benchmark using Gemma 4 31B in which LPX delivered 3,400 output tokens per second for 100,000-token contexts, which it said was four times the nearest alternative.

## Sources

- [NVIDIA Blog](https://blogs.nvidia.com/blog/vera-rubin-lpx-spectrum-x-nvlink-fusion/)

---
Canonical: https://techandbusiness.org/newswire/684pnZE8sDvrRlaqWPmiRl
Retrieved: 2026-08-24T17:46:29.845Z
Publisher: Tech & Business (techandbusiness.org)