NVIDIA L4-2Q
Data CenterA power-efficient data centre GPU built on the Ada Lovelace architecture, tailored for AI inference and media processing workloads.
Key Specifications
VRAM
2 GB GDDR6
Memory Bus
96-bit
FP16
67.2 TFLOPS
FP32
33.6 TFLOPS
TDP
72 W
Best Use Cases
AI Inference
Achieves high throughput for transformer-based AI models thanks to Tensor cores tuned for FP8 and INT8 operations within virtualised settings.
Video Encoding & Streaming
Comes with dedicated AV1 encoders and decoders for effective video transcoding, making it well-suited for live streaming and media delivery services.
Graphics Virtualization
Offers a robust virtual GPU experience for remote desktops and cloud gaming platforms, complete with professional-grade graphics capabilities.