logoalt Hacker News

jedbrooke • today at 4:51 AM • 1 reply • view on HN

> > one NVIDIA GB200 NVL72 That’s around ~$4-6 million in hardware cost (one rack, 72 GPUs + accompanying hardware).

that’s a good clarification, skimming some of the comments here I was thinking they trained it on a single GB200 gpu. THAT would be a huge win for indie AI

Edit: Nvidia GB200 does not refer to a single gpu, Nvidia’s naming scheme is very confusing. Considering past gpus were called H100, H200 etc, I thought GB200 would just be a newer GPU, but it does actually refer to their 30+ gpu rack scale systems. The claim of “we trained this on a single rack of gpus” is definitely much less impressive than “we trained this on a single gpu”

Replies

sheepscreek • today at 8:21 AM

> Nvidia GB200 does not refer to a single gpu, Nvidia’s naming scheme is very confusing. Considering past gpus were called H100, H200 etc, I thought GB200 would just be a newer GPU, but it does actually refer to their 30+ gpu rack scale systems.

It's even more confusing than that :)

    GB200 = 1 CPU + 2 B200 GPUs (packaged together)

    NV72 = A rack of 72 B200 GPUs (or 32 GB200 superchips)
Think of GB200 as something like Apple's 'Ultra' chip. Not exactly, but similar. They fuse the chips together with a very fast interconnect (connection).