Nvidia's dedicated inference accelerator Groq 3 LPX enters full production to supercharge AI agents
Nvidia has moved the Groq 3 LPX dedicated inference accelerator into full mass production to support agentic AI workloads. The hardware is a central component of the Vera Rubin platform and targets the low-latency AI inference market. Following a 20 billion dollar acquisition of Groq technology, Nvidia expects the associated rack systems to go online and begin delivery before the end of 2026. Initial deployments at Nebius are reported to deliver 3,400 tokens per second.
Listen to Live Briefing
Real-time synthesized voice briefing · Live Feeds Desk
- ✓ The Groq 3 LPX inference accelerator has entered full mass production.
- ✓ Nvidia acquired Groq technology in a 20 billion dollar deal.
- ✓ Groq 3 LPX racks are scheduled to be online and delivered before the end of 2026.
- ✓ The Groq 3 LPX is a component of the Vera Rubin platform.
What changed
Nvidia announced the Groq 3 LPX has entered full mass production with rack deliveries starting this year.
Live updates
-
Nvidia puts Groq 3 LPX inference accelerator into full production
Nvidia has moved the Groq 3 LPX dedicated inference accelerator into full mass production to support agentic AI workloads. The hardware is a central component of the Vera Rubin platform and targets the low-latency AI inference market. Following a 20 billion dollar acquisition of Groq technology, Nvidia expects the associated rack systems to go online and begin delivery before the end of 2026. Initial deployments at Nebius are reported to deliver 3,400 tokens per second.
Why it matters
This move shifts Nvidia's focus from AI model training toward real-world deployment. The Groq 3 LPX will be deployed at cloud providers alongside Vera central processors and Rubin graphics processors.
What is confirmed
- The Groq 3 LPX inference accelerator has entered full mass production.
- Nvidia acquired Groq technology in a 20 billion dollar deal.
- Groq 3 LPX racks are scheduled to be online and delivered before the end of 2026.
- The Groq 3 LPX is a component of the Vera Rubin platform.
Still unconfirmed
- Groq 3 LPX racks at Nebius deliver 3,400 tokens per second.
- Approximately half of Nvidia employees have a net worth exceeding 25 million dollars.
What to watch next
- Confirmation of delivery timelines for cloud provider deployments.
- Public release of official Groq 3 LPU benchmarks.
confidence 100%Sources used for this update (13)
- www.nba.com — NBA Offseason: Every free agency deal, extension & trade for all 30 ...
- www.nhl.com — NHL Free Agent Tracker
- CNBC — Nvidia says Groq racks will be online this year following $20 billion purchase
- NVIDIA Newsroom — NVIDIA Groq 3 LPX Now in Full Production With World-Class Speed for Agentic AI
- SiliconANGLE — Nvidia's dedicated inference accelerator Groq 3 LPX enters full production to supercharge AI agents
- The Register — What Nvidia's first Groq 3 LPU benchmarks tell us about its $20B gamble
- The Motley Fool — Nvidia’s $20 Billion Groq Bet Is Going Live Before the End of 2026. Here’s What It Means for Investors.
- NVIDIA Blog — With Groq 3 LPX in Full Production, NVIDIA Extends Vera Rubin Inference for Agents
- www.briefs.co — Nvidia's $20B Racks for Groq Begin Delivery This Year
- www.tradingkey.com — Nvidia Groq 3 LPX Enters Full Mass Production With Racks Online This Year, Boosting AI Inference Performance
- yellow.com — Nvidia Puts Groq 3 LPX Into Full Production for Agentic AI
- www.tekedia.com — Nvidia Puts $20bn Groq Acquisition Into Production to Secure AI Inference Market Share
Community Sentiment: How do you assess this situation?
Voice your perspective · Real-time aggregated sentiment from the Live Feeds community