NVIDIA L40S
GPU architecture NVIDIA Ada Lovelace
The most powerful general-purpose GPU accelerator for AI, graphics and computing
18,176 NVIDIA CUDA cores for advanced parallel computing
568 NVIDIA Tensor cores for AI model training and inference
142 RT cores for real-time graphics rendering and ray tracing
48 GB of GPU memory with ECC for working with large AI models and 3D scenes
Memory capacity up to 864 GB/s
Interface PCIe 4.0 x16
Passive cooling designed for servers and data centres
Maximum power consumption: 350 W
Free shipping from €300
Promocja cenowa na model HDR-15-5
Product intended for professional use only
NVIDIA L40S
Description
NVIDIA L40S - versatile GPU accelerator for AI, graphics and data centres
NVIDIA L40S Tensor Core GPU is one of the most versatile GPU accelerators for modern data centres. Based on the NVIDIA Ada Lovelace architecture, the chip combines massive computing power for artificial intelligence with advanced graphics rendering and video processing capabilities.
The L40S GPU is designed as a platform for a wide range of applications - from training and inference of artificial intelligence models, data analysis and video processing, to 3D graphics rendering and digital twin creation.
NVIDIA Ada Lovelace Architecture
The NVIDIA L40S GPU uses the NVIDIA Ada Lovelace architecture to deliver significant performance gains in both deep learning tasks and graphics and simulation applications.
The accelerator is equipped with 18,176 CUDA cores, 568 Tensor cores and 142 RT cores to accelerate computational operations, graphics rendering and data analysis used in artificial intelligence systems.
Additionally, the card offers 48 GB of GPU memory with ECC and a bandwidth of up to 864 GB/s to support very large AI models, graphics scenes and simulation applications.
CUDA cores
tensor cores
core RT
GPU memory
GPU for generative artificial intelligence
NVIDIA L40S is widely used in artificial intelligence systems and generative AI platforms. The accelerator enables AI models to be trained and run in production and data centre environments.
training and inference of LLM models
VLM and systems combining text, image and video
AI using enterprise knowledge
image and video analytics
big data and enterprise AI
AI-as-a-Service platforms
GPU for graphics, rendering and digital twins
With its RT cores and massive processing power, the NVIDIA L40S is perfect for graphics and simulation applications.
Accelerator applications include:
- rendering 3D graphics
- virtual manufacturing
- NVIDIA Omniverse platforms
- creating digital twins
- virtual workstations
- video processing and multimedia processing
GPU accelerator for modern data centres
The NVIDIA L40S is designed for server systems and GPU clusters used in data centres. The PCIe 4.0 x16 interface provides high bandwidth communication with the server system.
With passive cooling and a maximum power consumption of 350 W, the card is designed for professional GPU platforms supporting demanding computing workloads.
Technical Specification
| GPU Architecture | NVIDIA Ada Lovelace Architecture |
|---|---|
| GPU Memory | 48GB GDDR6 with ECC |
| Memory Bandwidth | 864 GB/s |
| Interconnect Interface | PCIe Gen4 x16: 64 GB/s bidirectional |
| CUDA® Cores (Ada Lovelace Architecture) | 18,176 |
| NVIDIA Third-Generation RT Cores | 142 |
| NVIDIA Fourth-Generation Tensor Cores | 568 |
| RT Core Performance | 209 TFLOPS |
| FP32 | 91.6 TFLOPS |
| TF32 Tensor Core | 183 | 366* TFLOPS |
| BFLOAT16 Tensor Core | 362.05 | 733* TFLOPS |
| FP16 Tensor Core | 362.05 | 733* TFLOPS |
| FP8 Tensor Core | 733 | 1,466* TFLOPS |
| Peak INT8 Tensor | 733 | 1,466* TOPS |
| Peak INT4 Tensor | 733 | 1,466* TOPS |
| Form Factor | 4.4" (H) x 10.5" (L), dual slot |
| Display Ports | 4x DisplayPort 1.4a |
| Max Power Consumption | 350 W |
| Power Connector | 16-pin |
| Thermal Solution | Passive |
| Virtual GPU (vGPU) Software Support | Yes |
| vGPU Profiles Supported | See the virtual GPU licensing guide |
| NVENC | NVDEC | 3x | 3x (includes AV1 encode and decode) |
| Secure Boot with Root of Trust | Yes |
| NEBS Ready | Level 3 |
| MIG Support | No |
| NVIDIA® NVLink® Support | No |
| Note | * With sparsity |
