g2.2xlarge vs p3.2xlarge

Instance Typeg2.2xlargep3.2xlarge
Instance FamilyGPU instanceGPU instance
DetailsObsolete. Not recommended for use
Machine Learning (ML), 3D visualizations, graphics-heavy remote workstations, 3D rendering, application streaming, video encoding, and server-side graphics tasks.

g – GPU (Graphics Processing Unit)
2 – Generation
2xlarge – Size
GPU intensive tasks like machine/deep learning, high-performance computing

p – Performance / GPU (Graphics Processing Unit) accelerated
3 – Generation
2xlarge – Size
vCPUs88
Memory15 GiB61 GiB
CPU Architecturen/an/a
ProcessorIntel Xeon E5-2670 (Sandy Bridge)Intel Xeon E5-2686 v4 (Broadwell)
Threads Per Core00
Accelerators
GPUnono
GPUs11
Inference Acceleratornono
Accelerator Memory16 GiB
FPGAnono
Instances
Sizesg2.2xlarge, g2.8xlargep3.16xlarge, p3.2xlarge, p3.8xlarge
Generationsg2.2xlarge, g5.2xlarge, g6.2xlarge, g7.2xlarge
Free Tiernono
Burstablenono
Hibernationnono
EC2 Compute Units2631
Instance Storage1 x 60 SSDEBS only
EBS (Elastic Block Store)
Dedicated Throughput1750 MBps
Networking
Networking PerformanceModerateUp to 10 Gigabit
Enhanced Networkingnoyes
IPv6 Supportnono
EFA Supportnono
Encryption in Transit Supportnono
ENA SRD Supportnono
Avg Price Diff1.00x4.58x

Regional Prices

US Dollar ($)
Per Hour
Linux
Shared Tenancy
On Demand
Geography
Region
g2.2xlarge
p3.2xlarge
EuropeEurope (Ireland) (eu-west-1)0.7020n/a
HiddenHidden (hidden-1)0.70203.3050
HiddenHidden (hidden-2)0.77203.3660
HiddenHidden (hidden-3)0.89803.5890
HiddenHidden (hidden-4)0.89803.6720
HiddenHidden (hidden-5)0.89803.8230
HiddenHidden (hidden-6)1.00004.1940
HiddenHidden (hidden-7)n/a4.2340
HiddenHidden (hidden-8)n/a4.2340
HiddenHidden (hidden-9)n/a4.2340
USUS East (Ohio) (us-east-2)n/a3.0600
USUS East (Virginia) (us-east-1)0.65003.0600
USUS West (Oregon) (us-west-2)0.65003.0600
Activate subscription to see all regions and unlock all features  

Related Comparisons

Other instances worth weighing against these.