QuData

Rent L4 by the Hour by QuData Ai

Explore the specifications and benchmarks of L4. Compare hardware configurations and performance metrics to optimize your AI and video workloads with an energy-efficient GPU architecture.

GPU Description

Explore the specifications and benchmarks of L4. Compare hardware configurations and performance metrics to optimize your AI and video workloads with an energy-efficient GPU architecture.

GPU Characteristics

GPU typeL4
Connecting GPUPCIe
GPU model nameNVIDIA L4
Driver version535.183.01
GPU memory24GB GDDR6
Power Limit (W)72.0
GPU temperature (°C)42
GPU Clock Speed (MHz)2040
Memory Clock Speed (MHz)7001
Pstate0

GPU Configuration

CUDA cores7424
Tensor core240 (4th generation)
Memory bandwidth300 GB/s
Support for FP16/INT8Yes
ArchitectureAda Lovelace
VirtualizationNVIDIA vGPU

Benchmarks

ffmpeg~15ms
Coremark (iterations per second)~45000-55000
Llama2 Inference (tokens per second)~85-110
Tensorflow Mixed Training~2.1-2.8
Stable Diffusion (images/min)~25-35
Video Encoding (1080p)~180-220 fps

Providers with L4