Ada Lovelace GPU

NVIDIA L4

24GB GDDR6 | 242 TFLOPS FP16 | 300 GB/s bandwidth

From $0.350 /hr

Inference Video transcoding Light AI workloads

Specifications

VRAM

24 GB GDDR6

FP16

242 TFLOPS

FP8

485 TFLOPS

FP4

N/A

Memory BW

300 GB/s

TDP

72W

Interconnect

PCIe Gen4

Architecture

Ada Lovelace

Cloud GPU Pricing (4 offers)

ProviderInstance TypevCPUsRAMPrice/hrPrice/moSpot PriceAvailabilityAction
Vast.aiCheapest
l4_24gb832 GB$0.350/hr$255.50/mo
$0.260-25.7%
AvailableRent on Vast.ai
RunPod
l4-24gb862 GB$0.390/hr$284.70/mo
$0.270-30.8%
AvailableDeploy on RunPod
Google Cloud Platform
g2-standard-8832 GB$0.520/hr$379.60/mo
$0.210-59.6%
AvailableDeploy on Google Cloud
Google Cloud Platform
g2-standard-8832 GB$0.570/hr$416.10/mo
$0.230-59.7%
AvailableDeploy on Google Cloud
Last updated 57h ago

Compare With Other GPUs

Frequently Asked Questions

What is the cheapest NVIDIA L4 cloud provider?
The cheapest NVIDIA L4 is available on Vast.ai at $0.350/hr (l4_24gb).
How much does NVIDIA L4 cost per hour?
NVIDIA L4 cloud GPU pricing ranges from $0.350/hr to $0.570/hr depending on the provider and configuration.
What are the specs of NVIDIA L4?
NVIDIA L4 features 24GB GDDR6 memory, 242 TFLOPS FP16 performance, 300 GB/s memory bandwidth, and 72W TDP. Architecture: Ada Lovelace.
Is NVIDIA L4 good for AI training?
NVIDIA L4 is primarily designed for: Inference, Video transcoding, Light AI workloads. For large-scale training, consider higher-tier GPUs.

Related GPUs