GPUs & AI Accelerators

NVIDIA HGX B200

Name: NVIDIA HGX B200
Brand: NVIDIA
SKU: HGX B200

HGX B200 (NVIDIA)

Tdp W

1000

Interconnect

1,800 GB/s NVLink between GPUs via NVIDIA NVSwitch™

Specifications

Blurred values are subscriber-only. Sign in to start a free trial — 2 full pages a day — or subscribe for unlimited access.

Memory Bandwidth Tb S	7.7
Interconnect Bandwidth Gb S	14.4
Interconnect	1,800 GB/s NVLink between GPUs via NVIDIA NVSwitch™
Tdp W	1000
Memory Type	HBM3E
Fp16 Bf16 Tflops Dense	2250
Fp8 Tflops Dense	4500
Fp16 Bf16 Tflops Sparse	4500
Fp32 Tflops	75
Int8 Tops Dense	4500
Fp4 Tflops Dense
Fp4 Tflops Sparse
Fp64 Tflops
Fp8 Tflops Sparse
Int8 Tops Sparse
Product Name
System Total Memory Gb

NVIDIA Blackwell GPUs \| Grace CPUs
CPU Cores
Total NVFP4 Tensor Core
Total FP8/FP6 Tensor Core
Total Fast Memory
Total Memory Bandwidth
FP4 Tensor Core (Individual Blackwell GPU)
FP8/FP6 Tensor Core (Individual Blackwell GPU)
INT8 Tensor Core (Individual Blackwell GPU)
FP16/BF16 Tensor Core (Individual Blackwell GPU)
TF32 Tensor Core (Individual Blackwell GPU)
FP32 (Individual Blackwell GPU)
FP64/FP64 Tensor Core (Individual Blackwell GPU)
GPU Memory \| Bandwidth (Individual Blackwell GPU)
Server Options
Key Feature - Blackwell GPUs
Key Feature - HBM3E memory
Key Feature - NVLink between GPUs
Key Feature - Real-time LLM inference
Key Feature - Training performance
Real-time inference vs Hopper
GPT-MoE-1.8T Real-Time Throughput (Output Tokens per Second per GPU)
NVLink GPU-to-GPU interconnect (fifth-generation)
LLM training speedup
GPT-MoE-1.8T Model Training Speedup
Energy efficiency vs Hopper