Hardware
Compare GPUs
Pick 2–4 data-center accelerators and compare them side by side — memory, bandwidth, dense FP16 / FP8 / FP4 compute, board power, perf-per-watt, and interconnect. Figures are drawn from published vendor datasheets; every column links through to matching nodes you can request a quote on. No pricing — compute is quoted per configuration on request.
| Spec | NVIDIANVIDIA H100 SXM | NVIDIANVIDIA H200 SXM | NVIDIANVIDIA B200 (HGX) |
|---|---|---|---|
| Architecture | Hopper | Hopper | Blackwell |
| GPU memory | 80 GB | 141 GB | 180 GB▲ |
| Memory type | HBM3 | HBM3e | HBM3e |
| Memory bandwidth | 3.35 TB/s | 4.8 TB/s | 7.7 TB/s▲ |
| FP16 dense | 989.5 TFLOPS | 989.5 TFLOPS | 2,250 TFLOPS▲ |
| FP8 dense | 1,979 TFLOPS | 1,979 TFLOPS | 4,500 TFLOPS▲ |
| FP4 dense | — | — | 9,000 TFLOPS▲ |
| Board power (TDP) | 700 W▲ | 700 W▲ | 1000 W |
| Perf / watt (FP16) | 1.41 TFLOPS/W | 1.41 TFLOPS/W | 2.25 TFLOPS/W▲ |
| Interconnect | NVLink 4 · 900 GB/s | NVLink 4 · 900 GB/s | NVLink 5 · 1800 GB/s |
| Scale-up domain | 8 GPUs▲ | 8 GPUs▲ | 8 GPUs▲ |
| Form factor | SXM5 | SXM5 | SXM (HGX B200) |
| Power & cooling | ~5.6 kW / 8-GPU node Liquid-cooled Air-cooled | ~5.6 kW / 8-GPU node Air-cooled | ~8.0 kW / 8-GPU node Air-cooled Liquid-cooled |
| Availability | View NVIDIA H100 SXM specs →Datasheet ↗ | View NVIDIA H200 SXM specs →Datasheet ↗ | View NVIDIA B200 (HGX) specs →Datasheet ↗ |
Specs as of · sourced from published vendor datasheets. FLOPS are dense (no sparsity); “—” marks a precision the chip does not support. Power figures are approximate, accelerators only (excludes host CPUs, networking, and cooling overhead). Pricing on request — confirm the exact configuration when you request a quote.