NVIDIA H200 GPU 规格与特性 | AI生成和翻译

Home 2026.03

Question: What are the key specifications and features of the NVIDIA H200 GPU?

Answer: NVIDIA H200 是基于相同 Hopper architecture 构建的 H100 显存增强进化版。虽然它与其前代产品共享相同的核心计算引擎,但 H200 对其内存子系统进行了重大升级,使其成为第一款使用 HBM3e (High Bandwidth Memory 3e) 的 GPU。

## Key Technical Specifications

H200 的主要区别在于其显存容量和带宽的大幅提升,这直接解决了 Large Language Model (LLM) 推理和训练中的“内存墙”问题。

Feature NVIDIA H100 (SXM) NVIDIA H200 (SXM) Improvement
Architecture Hopper (4nm) Hopper (4nm) -
GPU Memory 80 GB HBM3 141 GB HBM3e +76%
Memory Bandwidth 3.35 TB/s 4.8 TB/s +43%
FP8 Tensor Core 3,958 TFLOPS* 3,958 TFLOPS* Identical
FP64 (Non-Tensor) 34 TFLOPS 34 TFLOPS Identical
TDP (Power) 700W 700W Identical
Interconnect NVLink 4.0 (900 GB/s) NVLink 4.0 (900 GB/s) Identical

*Performance figures include sparsity.


## Core Features & Innovations

## Performance Impact

H200 专为在内存带宽是瓶颈的 inference-heavy 环境中表现出色而设计:

  1. LLM Inference: 与 H100 相比,它在 Llama 2 70B 等模型上的性能提升高达 1.9 倍
  2. Scientific Computing (HPC): 对于内存密集型仿真(如 MILC 或天气建模),增加的带宽使其相比传统双路 CPU 系统实现了 110 倍的加速
  3. TCO Efficiency: 由于 H200 可以更高效地处理更大的 Batch Size 和更长的 Context Window,尽管初始硬件成本较高,但通常会降低生成每个 token 的总拥有成本 (TCO)。

Would you like me to compare the H200 specifically against the newer Blackwell B200 architecture?


Back Donate