NVIDIA H200 GPU servers are now available for order. Learn more
The most powerful universal GPU for the data center, delivering end-to-end acceleration for the next generation of AI-enabled applications.
Experience breakthrough multi-workload performance with the NVIDIA L40S GPU. Combining powerful AI compute with best-in-class graphics and media acceleration, the L40S GPU is built to power the next generation of data center workloads. With shorter lead times than the H100, this GPU is ideal for inference workloads.
Unprecedented computational power for scientific research and simulations with large datasets and intricate calculations.
Harness the power of efficient neural network processing to enable swift and accurate predictions.
Powering immersive gaming environments, architectural visualizations, and cinematic renderings.
From video transcoding to image manipulation, ensure efficient and rapid processing for content creation and distribution.
| NVIDIA L40S PCIe | Specifications |
|---|---|
| GPU Architecture | NVIDIA Ada Lovelace Architecture |
| FP64 TFLOPS | N/A |
| FP64 Tensor Core TFLOPS | N/A |
| FP32 TFLOPS | 91.6 |
| TF32 Tensor Core TFLOPS | 183 | 366* |
| BFLOAT16 Tensor Core TFLOPS | 362.05 | 733* |
| FP16 Tensor Core | 362.05 | 733* |
| FP8 Tensor Core | 733 | 1,466* |
| INT8 Tensor Core | 733 | 1,466* TOPS |
| GPU memory | 48GB GDDR6 with ECC |
| GPU memory bandwidth | 864GB/s |
| Decoders | 3 NVENC | 3 NVDEC |
| Max thermal design power (TDP) | 350W |
| Multi-Instance GPUs | No |
| Form factor | PCIe dual-slot air-cooled |
| NVLink Support | No |
| *With Sparsity | View Full Specs |