The NVIDIA A40 is an enterprise-class GPU built on the Ampere architecture, featuring 48 GB of memory with 696 GB/s of memory bandwidth and a 300 W TDP. It delivers 37.4 TFLOPS of FP32 performance and 150 TFLOPS of FP16 tensor performance. Currently available from 3 providers starting at $0.29/GPU/hour, with a market median of $1.74/GPU/hour across 13 configurations.
Cheapest
$0.290/hr
Vast.ai
Median
$1.736/hr
across 13 offerings
Most expensive
$2.333/hr
Vultr
90-day trend
+43.5%
median rate
Hardware specifications
Same across all providers
Memory
48 GB
FP16 performance
150 TFLOPS
peak
TDP
300 W
Memory bandwidth
696 GB/s
Architecture
Ampere
FP32 performance
37.4 TFLOPS
Brand
NVIDIA
Series
A40
Market price history
Median price across all providers
4 offerings from 3 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 A40 cost per hour?
The A40 starts at $0.29 per GPU-hour, with a median of $1.74 across 13 available configurations. Actual pricing depends on the provider, region, and whether you rent on-demand, spot or reserved.
Which cloud providers offer the A40?
4 providers currently list the A40: Vultr, Runpod, Sesterce Cloud, Vast.ai. Compare their hourly pricing, regions and machine specs in the table above.
How much VRAM does the A40 have?
The A40 comes with 48 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.
Where is the A40 cheapest?
The lowest on-demand price we currently track for the A40 is $0.29 per GPU-hour at Vast.ai. Because providers update pricing and availability frequently, check the live table above before you launch.