GB200
GB200 is a NVIDIA CPU and GPU superchip based on the Grace CPU + 2x B200 architecture, first released in 2025.
Built from BenchGecko data as of April 14, 2026 · updates when the data changes
GB200 is a NVIDIA CPU and GPU superchip based on the Grace CPU + 2x B200 architecture, first released in 2025.
Basic
The NVIDIA GB200 Grace Blackwell is an AI CPU and GPU superchip made by NVIDIA. Peak throughput is 4,500 TFLOPS at FP16/BF16 and 9,000 TFLOPS at FP8. It carries 384 GB of HBM3e with 16 TB/s of memory bandwidth. Rated power (TDP) is 2,700 W. It is built on N4P at TSMC.
Deep
In the BenchGecko dataset it sits in the frontier tier: current-generation flagship silicon shipping at scale to hyperscalers. It is followed by the GB300. Disclosed buyers include Oracle and CoreWeave. Specs come from manufacturer datasheets; the spec card on this page shows the dataset values and their as-of date.
Expert
That is 1.67 FP16 TFLOPS per watt. Memory bandwidth per unit of compute is 3.56 GB/s per FP16 TFLOP: a higher ratio helps memory-bound inference, while peak TFLOPS matter more for compute-bound training. Fabrication: Taiwan. Real throughput depends on the model, precision, batch size and software stack, so compare tokens per second per dollar for your own workload.
Depending on why you're here
- ·GB200: 4,500 TFLOPS FP16/BF16 · 9,000 TFLOPS FP8
- ·Process: N4P at TSMC
- ·Tier: frontier
- ·384 GB of HBM3e per chip
- ·Cloud availability in the dataset: CoreWeave and Oracle Cloud
- ·Compare it with other chips on /hardware/gb200
- ·Disclosed buyers: Oracle and CoreWeave
- ·NVIDIA · fabbed at TSMC
- ·Supply tightness is tracked on /hardware
- ·GB200 is a chip built to run AI, made by NVIDIA
- ·It has 384 GB of fast memory so large models fit
- ·Companies buy or rent these to train and serve AI models
Frequently Asked Questions
Read the primary sources
- NVIDIA GB200 NVL72www.nvidia.com