NVIDIA L40S
Power your inference workloads with our NVIDIA L40S infrastructure. Deploy scalable clusters instantly, now available in our Sweden data center. Powered by the Ada Lovelace architecture and cutting-edge features, the L40S brings next-level performance and exceptional processing power to handle intensive tasks, such as AI inference and training.
NVIDIA L40S
Infrastructure and technology partners
Perfect for a range of workloads
Deploying AI based workloads on CUDO Compute is easy and cost-effective. Follow our AI related tutorials.
Deploying rendering based workloads on CUDO Compute is easy and cost-effective.
From video editing to image generation, virtualization is ideal for your content creation needs.
Purpose-built L40S clusters, designed and managed by CUDO
Deployed across 16 ISO-certified data centres
From 8 to 1,000+ GPUs in a single deployment
NVIDIA Quantum-X800 InfiniBand or Spectrum-X Ethernet networking
Expert rack-level design, installation, and benchmarking before handoff
24/7 monitoring, management, and engineering support
Compatible with Slurm, Kubernetes, and NVIDIA Base Command
Available at the most cost-effective pricing
Launch your AI products faster with on-demand GPUs and a global network of data center partners
Bare metal
Powered by renewable energy
No noisy neighbors
SpectrumX local networking
300Gbps external connectivity
NVMe SSD storage
Clusters
Deploy and manage powerful, scalable GPU clusters.
Scale up & down as needed
Production ready in minutes
Infiniband networking support
Manage with our CLI, dashboard & API
On-platform storage tooling
Specifications
Browse specifications for the NVIDIA L40S GPU
Starting from
Contact us for pricing
Architecture
NVIDIA Ada Lovelace
GPU
8x NVIDIA L40S GPUs
GPU memory
48GB GDDR6 with ECC
NVIDIA Ada Lovelace Architecture-Based CUDA® Cores
18,176
NVIDIA Fourth-Generation Tensor Cores
568
PCIe
PCIe Gen4
PCIe Gen4 x16 interconnect
64 GB/s bidirectional bandwidth
System power usage
~4 to 5 kW max
CPU
Dual 4th or 5th Gen Intel Xeon Scalable Processors (e.g., Platinum 8480+) or AMD EPYC 9004 Series equivalents
System memory
1 TB to 2 TB DDR5 ECC memory
Networking
Up to 4x single-port NVIDIA ConnectX-7 NICs (Up to 400 Gb/s) or NVIDIA BlueField-3 DPUs for scale-out Ethernet clustering (Spectrum-X)
Management network
1GbE onboard network interface card (NIC) with RJ45. Host baseboard management controller (BMC) with RJ45
Storage
OS: 2x 1.92 TB NVMe M.2 (Boot drives), internal storage: 2x to 8x 3.84 TB NVMe U.2/U.3 (Partner configurable)
Software
NVIDIA AI Enterprise (optimized AI software suite included), NVIDIA Omniverse Enterprise, Ubuntu / Red Hat Enterprise Linux / Rocky Linux
Rack units (RU)
4
Operating temperature
5-30°C (41-86°F)
Ideal uses cases for the NVIDIA L40S GPU
Explore uses cases for the NVIDIA L40S including Data science and AI, Rendering and 3D graphics, High-performance virtual workstations.
Data science and AI
The L40S GPU offers powerful training and inference performance, allowing professionals to reduce the time to completion for model training and development as well as data preparation workflows.
Rendering and 3D graphics
Powered by the latest fourth-generation Tensor Core and featuring enhanced AI capabilities, the L40S is the top choice for artists and content creators to handle complex rendering and graphics tasks.
High-performance virtual workstations
When combined with NVIDIA RTX Virtual Workstation (vWS) software, the L40S allows professionals to access the most demanding applications from anywhere with awe-inspiring performance that rivals physical workstations.
Blog
Resources
- Emmanuel Ohiri
Resources
- Emmanuel Ohiri
Resources
- Emmanuel Ohiri
Resources
- Emmanuel Ohiri
Resources
- Emmanuel Ohiri
Resources
- Emmanuel Ohiri
Browse alternative GPU solutions for your workloads
Access a wide range of performant NVIDIA and AMD GPUs to accelerate your AI, ML & HPC workloads
NVIDIA H100 PCIe
Price on request
Scale with high performance H100 GPUs on our reserved cloud.
