跳到主要内容Skip to main content

← 返回硬件算力← Back to Compute

加速卡Accelerators

NVIDIA H200 SXMNVIDIA H200 SXM

回答与 H100 同功耗档、显存翻到 141GB 的卡是什么水平,用于判断「模型能不能整卡放下」。注意官方在该页标注规格为初步数据、可能变动,采购前须回到最新 datasheet 复核。不回答实际推理吞吐:页面上的加速倍数来自厂商特定 batch 与序列长度条件。Answers what a card at the same power tier as H100 but with 141 GB of memory represents, which is what a "does the model fit on one card" decision needs. The vendor marks these figures as preliminary and subject to change on this page, so the current datasheet must be re-checked before procurement. It does not answer measured inference throughput: the speed-up multiples on the page come from specific vendor batch sizes and sequence lengths.

关键参数Key specs

memory
141 GB HBM3e
memory bandwidth
4.8 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 18 GB each

官方原文怎么说What the source says

GPU Memory 141GB GPU Memory Bandwidth 4.8TB/s
1 https://www.nvidia.com/en-us/data-center/h200/
Max Thermal Design Power (TDP) Up to 700W (configurable)
2 https://www.nvidia.com/en-us/data-center/h200/
Preliminary specifications. May be subject to change.
3 https://www.nvidia.com/en-us/data-center/h200/

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/h200/
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