NVIDIA · Datacenter System
DGX B200 (8× B200)
Blackwell
Prefill · prompt processing
Not benchmarked
Inference · generation speed
Not benchmarked
GPU / CPU chip
NVIDIA B200
RAM / VRAM
1,440 GB GPU total
No verified model-specific throughput measurement is published here yet. Prefill and generation rates depend on the model, precision, batch size and runtime.
Hardware specifications
| Product family | DGX |
| Model / configuration | DGX B200 |
| Released | 2024 |
| Manufacturer | NVIDIA |
| Hardware category | Datacenter System |
| Architecture | Blackwell |
| Form factor | Rackmount system |
| Accelerator model | NVIDIA B200 |
| Accelerator count | 8 |
| Interconnect | NVSwitch / NVLink |
Where to buy
No verified retailer listings have been added for this hardware yet.
Retailer links do not guarantee stock or a current price.
Observed prices
No source-backed price observations recorded yet.
Historical observations retain their original currency. Prices are not converted or adjusted for regional taxes.
Memory & bandwidth
| Primary memory (comparison) | 1,440 GB GPU total |
| Memory technology | HBM3e (8 GPUs) |
| Memory per GPU | 180 GB |
| Total GPU memory | 1,440 GB |
| GPU / system bandwidth | 64,000 GB/s total |
| GPU bandwidth | 8,000 GB/s |
| Power | 14,300 W |
System memory, aggregate GPU memory and memory available to one accelerator are separate measurements. Do not treat total multi-GPU memory as a single unified pool.
System accelerators
| 8× | B200 SXM |
Inference runtimes
Runtime support is not a model throughput or memory-fit benchmark.
1,440 GB aggregates eight 180 GB independent GPU memories.