NVIDIA Groq 3 LPX in full production, hits 3,400 tokens/sec
NVIDIA's Groq 3 LPX inference accelerator is now in full production, delivering 3,400 output tokens per second on Gemma 4 31B with 100K context in Artificial Analysis benchmarks, 4x faster than the nearest alternative. Nebius is the first AI cloud to adopt it.
How this story unfolded
3 days · 6 reports · 2 community posts · 8 of 10 shown
- Aug 22
- Aug 24
With Groq 3 LPX in Full Production, NVIDIA Extends Vera Rubin Inference for Agentsblogs.nvidia.com
NVIDIA Groq 3 LPX Now in Full Production With World-Class Speed for Agentic AInvidianews.nvidia.com
NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Wattdeveloper.nvidia.com
Inference on steroid: NVIDIA’s Groq 3 LPX is now in full production, adding a dedicated...
- Aug 25
NVIDIA by email
Get an email when NVIDIA has news
No news that day, no email.
More stories today
- OpenAI disrupts Russian covert influence campaign using AI
- Theo: Turn off Claude Code's Memory
- MiniMax H3 tested for Gaussian splatting
- AI drug-theft detection at hospitals fails without human oversight
- Chinese military thinkers outline AI's role in future warfare