跳到主要内容Skip to main content

← 返回硬件算力← Back to Compute

加速卡Accelerators

NVIDIA L40SNVIDIA L40S

回答一张兼顾图形与推理的 PCIe 卡的算力档位与功耗上限。不回答显存类型与带宽:官方该页只给容量、未给颗粒类型与带宽数值,按「查不到留空」处理,需要时查其 datasheet。Answers the compute tier and power ceiling of a PCIe card that covers both graphics and inference. It does not answer memory type or bandwidth: the vendor page states capacity only, so those fields are left empty rather than guessed, and should be read from the datasheet when needed.

关键参数Key specs

memory
48 GB
max power
350 W
form factor
PCIe, dual-slot air-cooled
FP32
91.6 TFLOPS
TF32 tensor, sparsity
366 TFLOPS
FP8 tensor, sparsity
1,466 TFLOPS
RT core
212 TFLOPS

官方原文怎么说What the source says

FP32 91.6 teraFLOPS TF32 Tensor Core 366 teraFLOPS* FP16 733 teraFLOPS* FP8 1,466 teraFLOPS* RT Core Performance 212 teraFLOPS Max Power Consumption 350W
1 https://www.nvidia.com/en-us/data-center/l40s/
48 gigabytes (GB) of memory capacity
2 https://www.nvidia.com/en-us/data-center/l40s/

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/l40s/
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