Nvidia L40 48GB

NVIDIA L40 GPU

The NVIDIA L40 is a cutting-edge GPU built on the Ada Lovelace architecture, designed to tackle high-performance AI inference, machine learning, and visualization workloads. With powerful computational and graphics capabilities, the L40 is ideal for professionals working on advanced AI models, data analysis, real-time inference, and complex simulations.

Optimized for AI inference and GPU-accelerated rendering, the L40 delivers exceptional performance in deep learning applications, enhancing both training and real-time deployment of AI models. It also supports high-end visualization tasks, including 3D rendering, virtual environments, and scientific computing. Equipped with a substantial memory capacity and outstanding processing power, the L40 excels in data centers, workstations, and HPC environments where demanding AI workloads and visual applications are a priority.

Whether you’re developing AI-driven innovations, conducting data-intensive research, or rendering complex visual simulations, the NVIDIA L40 GPU is engineered to help you achieve high-performance results with unmatched efficiency and scalability.

Specifications:

GPU Architecture: NVIDIA Ampere
NVIDIA Ada Lovelace architecture-
based CUDA Cores: 18,176
NVIDIA third-generation RT Cores: 142
Tensor Cores: 568 (Fourth-generation Tensor Cores)
GPU Memory: 48 GB
Memory Type: GDDR6
Memory Bandwidth: 864 GB/s
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
INT8 Tensor TOPS: 362 | 724
INT4 Tensor TOPS: 724 | 1448
Form Factor: PCIe 4.0
Thermal Design Power (TDP): 300W
Display Ports: 4 x DisplayPort 1.4a
Power Connector: 16-pin
Target Applications: AI model training, machine learning, deep learning inference, high-performance computing (HPC)