NVIDIA L4
Data CenterAn energy-saving, PCIe-form-factor data center GPU built on the Ada Lovelace architecture, tuned for AI inference and graphics workloads.
Key Specifications
VRAM
24 GB GDDR6
Memory Bus
256-bit
FP16
30.29 TFLOPS
FP32
30.29 TFLOPS
TDP
72 W
Best Use Cases
AI Inference
Provides high-speed tensor core acceleration for operating large language models and generative AI applications at scale with minimal latency.
Virtual Workstations
Supports immersive cloud-based graphics, CAD, and video editing experiences via hardware-accelerated encoding and decoding functionality.
GPU Cloud Services
Well-suited for service providers delivering cost-efficient, high-density GPU compute instances in the cloud thanks to its low per-core power consumption.