The NVIDIA L4 is an enterprise-class GPU built on the Ada Lovelace architecture, featuring 24 GB of memory with 300 GB/s of memory bandwidth and a 72 W TDP. It delivers 30.3 TFLOPS of FP32 performance and 121 TFLOPS of FP16 tensor performance. Currently available from 5 providers starting at $0.20/GPU/hour, with a market median of $0.90/GPU/hour across 19 configurations.
Cheapest
$0.200/hr
Vast.ai
Median
$0.900/hr
across 19 offerings
Most expensive
$1.050/hr
Runcrate
90-day trend
+45.5%
median rate
Hardware specifications
Same across all providers
Memory
24 GB
FP16 performance
121 TFLOPS
peak
TDP
72 W
Memory bandwidth
300 GB/s
Architecture
Ada Lovelace
FP32 performance
30.3 TFLOPS
Brand
NVIDIA
Series
L4
Market price history
Median price across all providers
5 offerings from 5 providers
Sorted by price ascending. Compare configurations side-by-side.
See more GPUs like this in
Want more from this page?
See incorrect data?
Frequently asked questions
How much does the L4 cost per hour?
The L4 starts at $0.20 per GPU-hour, with a median of $0.90 across 19 available configurations. Actual pricing depends on the provider, region, and whether you rent on-demand, spot or reserved.
Which cloud providers offer the L4?
6 providers currently list the L4: Runpod, Sesterce Cloud, Runcrate, Vast.ai, Scaleway, AceCloud. Compare their hourly pricing, regions and machine specs in the table above.
How much VRAM does the L4 have?
The L4 comes with 24 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.
Where is the L4 cheapest?
The lowest on-demand price we currently track for the L4 is $0.20 per GPU-hour at Vast.ai. Because providers update pricing and availability frequently, check the live table above before you launch.