How well does NVIDIA GB200 Superchip scale across multiple GPUs?

Resposta

NVIDIA GB200 Superchip performance headline: 4,500 FP16 TFLOPS, 150 FP32 TFLOPS, 16,000 GB/s bandwidth, 384 GB VRAM.

Converted into practical benchmarks: model training a 7B-parameter LLM in FP16 with reasonable batch sizes typically saturates compute before bandwidth; real-time serving on the same model is usually bandwidth-bound and tracks the 16,000 GB/s figure. Diffusion image generation benchmarks sit between the two — compute-heavy steps utilise tensor cores well, while attention blocks still touch bandwidth.

See the NVIDIA GB200 Superchip page for the full spec sheet and comparisons to related GPUs.