PNY NVIDIA L40S Graphics Card

BH #PNNVL40STCGK • MFR #NVL40STCGPU-KIT
Print
PNY NVIDIA L40S Graphics Card
Key Features
  • Designed for Data Centers
  • 18,176 CUDA Cores
  • Ada Lovelace Architecture
  • 48GB of ECC GDDR6 VRAM
Designed specifically for data centers, the PNY NVIDIA L40S Graphics Card delivers the performance for multi-model generative AI in addition to accelerating large language model training, 3D graphics rendering, and video workloads.
More Details
Discontinued
No Store Display
Ask an Expert
866-842-7675

PNY L40S Overview

Designed specifically for data centers, the PNY NVIDIA L40S Graphics Card delivers the performance for multi-model generative AI in addition to accelerating large language model training, 3D graphics rendering, and video workloads.

Based on the Ada Lovelace architecture, this universal GPU accelerates AI workloads and supported video applications with 18,176 CUDA cores. It also features 48GB of ECC GDDR6 VRAM with an 864 GB/s memory bandwidth 384-bit interface. Install the card into an available PCIe 4.0 x16 slot. The passively cooled design helps to ensure that it operates silently. External displays may be connected to the four DisplayPort 1.4a ports.

Fourth-Generation Tensor Cores
Hardware support for structural sparsity and optimized TF32 format with 568 tensor cores provides out-of-the-box performance gains for faster AI and data science model training. Accelerate AI-enhanced graphics capabilities with DLSS to upscale resolution with better performance in select applications.
Third-Generation RT Cores
With 142 RT cores, the NVIDIA L40S provides enhanced throughput and concurrent ray-tracing and shading capabilities. It also improves ray-tracing performance while accelerating renders for product design and architecture, engineering, and construction workflows.
Transformer Engine
Transformer Engine dramatically accelerates AI performance and improves memory utilization for both training and inference. Harnessing the power of the Ada Lovelace fourth-generation Tensor Cores, Transformer Engine intelligently scans the layers of transformer architecture neural networks and automatically recasts between FP8 and FP16 precisions to deliver faster AI performance and accelerate training and inference.
Data Center Ready
The L40S GPU is optimized for 24/7 enterprise data center operations and designed, built, tested, and supported by NVIDIA to ensure maximum performance, durability, and uptime. The L40S GPU meets the latest data center standards, is Network Equipment-Building System (NEBS) Level 3 ready, and features secure boot with root of trust technology, providing an additional layer of security for data centers.

PNY L40S Specs

Key Specs
GPU Model
NVIDIA L40S
Stream Processors
18,176
Dedicated AI Cores
No
Interface
PCI Express 4.0 x16
Video RAM
48 GB ECC GDDR6
Video Output
4x DisplayPort 1.4a
Power Connection
1x 16-Pin PCI Connector
GPU Width
Dual-Slot
GPU
GPU Model
NVIDIA L40S
Stream Processors
18,176
Clock Speed
Base Mode: 1065 MHz
Boost Mode: 2520 MHz
Dedicated AI Cores
No
Interface
PCI Express 4.0 x16
Supported APIs
No
Memory
Video RAM
48 GB ECC GDDR6
Memory Speed
9001 MHz (Effective)
Memory Interface Width
384-Bit
Memory Bandwidth
864 GB/s
Display Support
Video Output
4x DisplayPort 1.4a
Power Requirements
Max Power Consumption
350 W
Power Connection
1x 16-Pin PCI Connector
Compatibility
Expansion Slot Compatibility
Full Height
Height
4.4" / 111.8 mm
Length
10.5" / 266.7 mm
Width
Dual-Slot
OS Compatibility
Windows
Linux
General
Cooler Type
Passive Heatsink

PNY L40S Reviews

See any errors on this page?
Whatever You Need, We've Got It