# NVIDIA — With Groq 3 LPX in Full Production, NVIDIA Extends Vera Rubin Inference for Agents

- Company: NVIDIA (nvidia.com)
- Announced: 2026-08-24T15:00:41+00:00
- Category: product-launch
- Subject: AI platform
- Models affected: Gemma 4 31B
- Coverage: Covered by 21 outlets
- Source: https://blogs.nvidia.com/blog/vera-rubin-lpx-spectrum-x-nvlink-fusion/
- Record: https://forck.live/items/4369-with-groq-3-lpx-in-full-production-nvidia-extends-vera-rubin-inference-for

NVIDIA announced that its Groq 3 LPX inference accelerator is in full production, delivering 3,400 output tokens per second on Gemma 4 31B for 100,000-token long-context use cases, 4x faster than alternatives. The system is part of the Vera Rubin platform and is being adopted by partners like SpaceXAI, CoreWeave, and Nebius.

## Evidence

Verbatim from https://blogs.nvidia.com/blog/vera-rubin-lpx-spectrum-x-nvlink-fusion/:

> Announced today , the NVIDIA Vera Rubin rack-scale system NVIDIA Groq 3 LPX is in full production.

## Around this story

Outlets this record can name and link:

- Bloomberg: https://bloomberg.com/news/articles/2026-08-25/india-ai-data-center-firm-orders-9-000-nvidia-vera-rubin-systems
- Quartz: https://qz.com/nvidia-groq-3-lpx-inference-chip-full-production-082426
- Quartz: https://qz.com/spacex-nvidia-ai-satellites-orbit-2027-082526
- Tom's Hardware: https://tomshardware.com/pc-components/cpus/hot-chips-2026-nvidia-breaks-down-88-core-vera-cpu-spatial-multithreading-benchmarked-1-2-tb-s-socamm2-memory-agentic-workloads-detailed-and-more
- Tom's Hardware: https://tomshardware.com/tech-industry/big-tech/spacexai-will-deploy-standalone-nvidia-vera-cpus-for-groks-agentic-workloads
- Tech in Asia: https://techinasia.com/news/nvidia-groq-3-lpx-rack-enters-full-production
- Unite.AI — SpaceXAI Puts NVIDIA’s Vera CPU at the Center of Gigawatt-Scale Buildout: https://unite.ai/spacexai-puts-nvidias-vera-cpu-at-the-center-of-gigawatt-scale-buildout
- Blockchain.News — NVIDIA Groq 3 LPX Achieves 3,431 TPS Benchmark on Vera Rubin: https://blockchain.news/news/nvidia-groq-3-lpx-benchmark-vera-rubin
- MarketWatch: https://marketwatch.com/story/spacex-plans-to-put-nvidia-powered-ai-satellites-in-orbit-next-year-ab57083c
- DigiTimes — Nvidia Groq 3 LPX enters full production for faster agentic AI inference: https://digitimes.com/news/a20260825PR202.html
- Anadolu Ajansı …: https://aa.com.tr/en/science-technology/nvidia-begins-production-of-groq-ai-racks-after-20b-purchase/4036129
- Light Reading — SpaceXAI to use Nvidia 'Vera' chips for agentic AI apps: https://lightreading.com/ai-machine-learning/spacexai-to-use-nvidia-vera-chips-for-agentic-ai-apps-and-starmind-ai-satellites
- StorageReview.com — NVIDIA Groq 3 LPX Enters Full Production: 3,400 Tokens per Second at 100K Context, 256 LP30s per Rack: https://storagereview.com/news/nvidia-groq-3-lpx-enters-full-production-3400-tokens-per-second-at-100k-context-256-lp30s-per-rack

---

Record: https://forck.live/items/4369-with-groq-3-lpx-in-full-production-nvidia-extends-vera-rubin-inference-for
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md