The NVIDIA RTX 3070 is a consumer-grade GPU built on the Ampere architecture, featuring 8 GB of memory with 448 GB/s of memory bandwidth and a 220 W TDP. It delivers 20.4 TFLOPS of FP32 performance. Currently available from 1 provider starting at $0.05/GPU/hour, with a market median of $0.10/GPU/hour across 11 configurations.
Cheapest
$0.050/hr
Vast.ai
Median
$0.100/hr
across 11 offerings
Most expensive
$0.200/hr
Vast.ai
90-day trend
+11.1%
median rate
Hardware specifications
Same across all providers
Memory
8 GB
GDDR6X
TDP
220 W
Memory bandwidth
448 GB/s
Architecture
Ampere
FP32 performance
20.4 TFLOPS
Brand
NVIDIA
Series
GeForce RTX
Market price history
Median price across all providers
1 offering from 1 providers
Sorted by price ascending. Compare configurations side-by-side.
Want more from this page?
See incorrect data?
Frequently asked questions
How much does the RTX 3070 cost per hour?
The RTX 3070 starts at $0.05 per GPU-hour, with a median of $0.10 across 11 available configurations. Actual pricing depends on the provider, region, and whether you rent on-demand, spot or reserved.
Which cloud providers offer the RTX 3070?
1 providers currently list the RTX 3070: Vast.ai. Compare their hourly pricing, regions and machine specs in the table above.
How much VRAM does the RTX 3070 have?
The RTX 3070 comes with 8 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.
Where is the RTX 3070 cheapest?
The lowest on-demand price we currently track for the RTX 3070 is $0.05 per GPU-hour at Vast.ai. Because providers update pricing and availability frequently, check the live table above before you launch.