Datasheet
NVIDIA L40
Delivering unprecedented visual computing
performance for the data center.
From virtual workstation application to large-scale modeling and simulation,
modern visual computing and scientific workflows are growing in both complexity Accelerate Next-
and quantity. Enterprises need data center technology that can deliver extreme Generation Workloads
performance and scale with versatile capabilities to conquer the diverse computing
> NVIDIA Omniverse™ Enterprise
demands of these increasingly complex workloads.
> Rendering and 3D Graphics
The NVIDIA® L40 GPU delivers unprecedented visual computing performance for
the data center, providing next-generation graphics, compute, and AI capabilities. > High-Performance Virtual
Built on the revolutionary NVIDIA Ada Lovelace architecture, the NVIDIA L40 Workstations with NVIDIA RTX™
harnesses the power of the latest generation RT, Tensor, and CUDA cores to deliver Virtual Workstation (RTX vWS)
groundbreaking visualization and compute performance for the most demanding Software
data center workloads.
> AI Training and Data Science
Powered by the NVIDIA Ada Lovelace Architecture > Streaming and Video Content
Third-Generation RT Cores
Enhanced throughput and concurrent ray-tracing and shading capabilities improve
ray-tracing performance, accelerating renders for product design and architecture,
engineering, and construction workflows. See lifelike designs in action with
hardware-accelerated motion blur to deliver stunning real-time animations.
Fourth-Generation Tensor Cores
Hardware support for structural sparsity and optimized TF32 format provides
out-of-the-box performance gains for faster AI and data science model training.
Accelerate AI-enhanced graphics capabilities, including DLSS, delivering upscaled
resolution with better performance in select applications.
Large GPU Memory
Tackle memory-intensive applications and workloads like data science, simulation,
3D modeling, and rendering with 48GB of ultra-fast GDDR6 memory. Allocate
memory to multiple users with vGPU software to distribute large workloads among
creative, data science, and design teams.
Data-Center Ready
Designed for 24x7 enterprise data center operations with power-efficient hardware
and components, the NVIDIA L40 is optimized to deploy at scale and deliver
maximum performance for a diverse range of data center workloads. The L40
includes secure boot with root of trust technology providing an additional layer of
security, and is NEBS Level 3 compliant to meet the latest data center standards.
Packaged in a dual-slot, passively cooled and power-efficient design, the L40 is
available in a wide variety of NVIDIA-Certified Systems™ from leading OEM vendors.
NVIDIA L40 | Datasheet | 1
Technical Specifications*
GPU Architecture NVIDIA Ada Lovelace architecture
GPU Memory 48GB GDDR6 with ECC
Memory Bandwidth 864GB/s
Interconnect Interface PCIe Gen4x16: 64GB/s bi-directional
NVIDIA Ada Lovelace architecture-based 18,176
CUDA Cores
NVIDIA third-generation RT Cores 142
NVIDIA fourth-generation Tensor Cores 568
RT Core performance TFLOPS 209
FP32 TFLOPS 90.5
TF32 Tensor Core TFLOPS 90.5 | 181**
BFLOAT16 Tensor Core TFLOPS 181.05 | 362.1**
FP16 Tensor Core 181.05 | 362.1**
FP8 Tensor Core 362 | 724**
Peak INT8 Tensor TOPS 362 | 724**
Peak INT4 Tensor TOPS 724 | 1448**
Form Factor 4.4” (H) x 10.5” (L) - dual slot
Display Ports 4 x DisplayPort 1.4a
Max Power Consumption 300W
Power Connector 16-pin
Thermal Passive
Virtual GPU (vGPU) software support Yes
vGPU Profiles Supported See Virtual GPU Licensing Guide1
NVENC I NVDEC 3x l 3x (Includes AV1 Encode & Decode)
Secure Boot with Root of Trust Yes
NEBS Ready Level 3
MIG Support No
NVLink Support No
* Preliminary specifications, subject to change.
** With Sparsity.
Ready to get started?
To learn more about the NVIDIA L40 GPU, visit:
www.nvidia.com/L40
1. Coming in a future release of NVIDIA vGPU software.
© 2023 NVIDIA Corporation and affiliates. All rights reserved. NVIDIA, the NVIDIA logo, NVIDIA-Certified Systems,
NVIDIA Omniverse and NVIDIA RTX are trademarks and/or registered trademarks of NVIDIA Corporation and
affiliates in the U.S. and other countries. Other company and product names may be trademarks of the respective
owners with which they are associated. 2436245. Jan23
