BREAKING
CoreWeave Benchmarks Vera Rubin NVL72
0x
tokens per MW
0
Rubin GPUs per rack
0
Vera CPUs per rack
Live Silicon, Not Projections
CoreWeave testlive
Model: DeepSeek-R1
Measured on live silicon
Own cooling and networking
NVIDIA claimvendor
Up to 10x vs GB200 NVL72
Benchmarked on Kimi-K2 Thinking
~1/10 cost per million tokens
How the Deployment Rolled Out
1June 1 bring-up
2Dell XE9812 ships
3System validation
4Live benchmark
0x
throughput per MW
0
production ramp year
Efficiency Now Governs AI Capacity
AI NEWS BLITZ
CoreWeave says it ran the first live benchmarks on NVIDIA's Vera Rubin platform.