B200
B200 is a NVIDIA GPU based on the Blackwell SM100 architecture, first released in 2024.
Built from BenchGecko data as of April 14, 2026 · updates when the data changes
B200 is a NVIDIA GPU based on the Blackwell SM100 architecture, first released in 2024.
Basic
The NVIDIA B200 is an AI GPU made by NVIDIA, codenamed Blackwell. Peak throughput is 2,250 TFLOPS at FP16/BF16 and 4,500 TFLOPS at FP8. It carries 192 GB of HBM3e with 8 TB/s of memory bandwidth. Rated power (TDP) is 1,000 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 follows the H200 and is followed by the B300. Disclosed buyers include Meta, Microsoft and Oracle. Specs come from manufacturer datasheets; the spec card on this page shows the dataset values and their as-of date.
Expert
That is 2.25 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
- ·B200: 2,250 TFLOPS FP16/BF16 · 4,500 TFLOPS FP8
- ·Process: N4P at TSMC
- ·Tier: frontier
- ·192 GB of HBM3e per chip
- ·Cloud availability in the dataset: CoreWeave, Lambda and Together AI
- ·Compare it with other chips on /hardware/b200
- ·Disclosed buyers: Meta, Microsoft and Oracle
- ·NVIDIA · fabbed at TSMC
- ·Supply tightness is tracked on /hardware
- ·B200 is a chip built to run AI, made by NVIDIA
- ·It has 192 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 Blackwell architecturewww.nvidia.com
- GTC 2024 keynotewww.nvidia.com