NVIDIARelease: 2023
L40S PCIe Gen4 x16
Unparalleled AI and graphics performance for the data center. Ideal for generative AI, large language model training, rendering, 3D graphics, and video content AI training.
ArchitectureNVIDIA Hopper™
Cheapest RentMarket Data Unavailable
Hardware Intelligence Dossier
RT Cores
142
CUDA Cores
18176
GPU Memory
48GB GDDR6 with ECC
NEBS Ready
Level 3
FP32 TFLOPS
91.6
Form Factor
4.4" (H) x 10.5" (L), dual slot
MIG Support
No
Tensor Cores
568
Display Ports
4x DisplayPort 1.4a
NVENC | NVDEC
3x | 3x (includes AV1 encode and decode)
NVLink Support
No
FP8 Tensor Core
733
Power Connector
16-pin
GPU Architecture
NVIDIA Ada Lovelace Architecture
Memory Bandwidth
864GB/s
Max Power Consumption
350W
Workload Suitability
The high-performance accelerator is engineered for mass-scale AI applications. From large language model (LLM) fine-tuning to high-throughput inference serving, this variant provides extreme memory bandwidth.
Asset Insights
"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. It meets the latest data center standards, is Network Equipment-Building System (NEBS) Level 3 ready, and features secure boot with root of trust technology."
Last Intel Refresh:February 2026
Verified Market Rates
Pricing Matrix
No live market data available for this variant