跳到主要内容Skip to main content

← 返回硬件算力← Back to Compute

加速卡Accelerators

NVIDIA H100 SXMNVIDIA H100 SXM

回答数据中心训练与推理卡的显存容量、带宽、功耗与互联口径。不回答实际训练吞吐或单位算力价格:这里记的是官方规格表数字,且带稀疏标注,实测吞吐随框架、精度与模型结构变化。Answers the memory capacity, bandwidth, power and interconnect figures of a data-centre training and inference card. It does not answer real training throughput or price per unit of compute: these are vendor spec-sheet numbers with sparsity, and measured throughput varies with framework, precision and model shape.

关键参数Key specs

memory
80 GB HBM3
memory bandwidth
3.35 TB/s
max TDP
up to 700 W (configurable)
form factor
SXM
interconnect
NVLink 900 GB/s; PCIe Gen5 128 GB/s
FP8 tensor, sparsity
3,958 TFLOPS
MIG
up to 7 instances at 10 GB each

官方原文怎么说What the source says

GPU Memory 80GB 94GB
1 https://www.nvidia.com/en-us/data-center/h100/
GPU Memory Bandwidth 3.35TB/s 3.9TB/s
2 https://www.nvidia.com/en-us/data-center/h100/
Max Thermal Design Power (TDP) Up to 700W (configurable) 350-400W (configurable)
3 https://www.nvidia.com/en-us/data-center/h100/
Interconnect NVIDIA NVLink™: 900GB/s PCIe Gen5: 128GB/s
4 https://www.nvidia.com/en-us/data-center/h100/

资料与许可Source and licence

资料时间Source checked
2026-11-07
许可 / 类型Licence / kind
official-spec-page
许可说明Licence evidence
https://www.nvidia.com/en-us/data-center/h100/
类目Category
加速卡Accelerators

去官网看原页Open the official page →

← 返回硬件算力← Back to Compute