GB200
Productby NVIDIA
Heard in 4 episodes across 4 shows since Sep 2026
The NVIDIA GB200 is a data-center AI computing platform built around the Grace Blackwell superchip, combining NVIDIA Grace CPUs with Blackwell GPUs through a high-bandwidth coherent interconnect. It is designed for large-scale generative-AI model training and inference, and is deployed in systems such as the liquid-cooled GB200 NVL72 rack-scale platform, which links 36 Grace CPUs and 72 Blackwell GPUs into a single NVLink domain.
Discussed inAI & Tech60%Business40%
Episodes
4
across 4 shows
This week
0
episodes on 0 shows
Share of the conversation
Mentions of GB200 per 1,000 mentions of anything, 7-day rolling, across the podcasts PodLume Trends follows.
Show the data
| Day | Share (7-day) | Mentions |
|---|---|---|
| Sep 17 | 0.03‰ | 1 |
| Sep 25 | 0.03‰ | 1 |
| Oct 3 | 0.05‰ | 2 |
| Oct 7 | 0.08‰ | 1 |
Episodes
4 episodes featuring GB200, newest first
- Oct 7, 2026
AI infrastructure bets face a trillion-dollar revenue testBig Technology PodcastOct 7, 2026 - Oct 3, 2026
Recursive AI collides with science, warfare, and economic changeMoonshots with Peter DiamandisOct 3, 2026 - Sep 25, 2026
AI spending tests the limits of infrastructure and trustBloomberg TechSep 25, 2026 - Sep 17, 2026
Real-time video pushes generative AI toward interactive worldsThe a16z ShowSep 17, 2026