BREAKING
GB300 NVL72: Up to 25x Per Watt
Perf Per Watt vs Hopper
DeepSeek V4 Pro25
GLM 5.120
Kimi K2.610
0x
throughput per MW gain
0
GPUs over NVLink
Why Per Watt Matters Now
The PitchNVIDIA
Lower cost per token
Better operator margins
Benchmark to production
The CaveatsObservers
Limited independent testing
Numbers depend on workload
Heavy cooling demands
0kW
peak rack draw
0
target PUE
Efficiency Becomes The Metric
AI NEWS BLITZ
NVIDIA says its GB300 NVL72 delivers up to twenty-five times better performance per watt than Hopper.