Skip to main content

NVIDIA H200 (Hopper Refresh)

Product Overview

The NVIDIA H200, released in 2024, is a memory-upgraded version of the H100. The key change is the upgrade from 80GB HBM3 to 141GB HBM3e, with bandwidth increasing from 3.35 TB/s to 4.8 TB/s (+43%). This delivers significant performance gains for 70B+ parameter model inference, enabling single-GPU loading of longer contexts.

Core Specifications

ParameterValue
ArchitectureHopper GH100 (refresh)
Process NodeTSMC 4N
Transistor Count80 billion
Memory141 GB HBM3e
Memory Bandwidth4.8 TB/s (4,800 GB/s)
CUDA Cores16,896
Tensor Cores528 (4th Gen)
FP8 Tensor Core3,958 TFLOPS (sparse)
TDP700 W (SXM5)
InterconnectNVLink 4.0 (900 GB/s), PCIe 5.0
MIGUp to 7 instances
Form FactorSXM5 / PCIe 5.0

H100 vs H200 Comparison

MetricH100H200Improvement
Memory Capacity80 GB141 GB+76%
Memory TypeHBM3HBM3eFaster
Memory Bandwidth3.35 TB/s4.8 TB/s+43%
FP8 Compute3,958 TFLOPS3,958 TFLOPSSame
Price (Reference)~$25,000–30,000~$30,000–35,000+20%

Vendor Information

ParameterValue
ManufacturerNVIDIA Corporation
Official Websitehttps://www.nvidia.com
Product Pagehttps://www.nvidia.com/en-us/data-center/h200/
ReleaseNovember 2024 (first shipments)

Software & Drivers

Use Cases

  • Large model inference (70B+ single GPU)
  • Long-context (100K+ tokens) inference
  • Large model fine-tuning
  • HPC memory-bound workloads