r6g.2xlarge vs g4ad.2xlarge

Instance Typer6g.2xlargeg4ad.2xlarge
Instance FamilyMemory optimizedGPU instance
DetailsHigh-performance databases, data mining/analysis, in-memory databases, distributed large-scale caches, real-time processing apps for unstructured big data, Hadoop/Spark clusters, and other enterprise apps.

r – RAM / memory optimized
6 – Generation
g – AWS Graviton processor
2xlarge – Size
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)
4 – Generation
a – AMD processor
d – Instance store volume
2xlarge – Size
vCPUs88
Memory64 GiB32 GiB
CPU Architecturearm64x86_64
ProcessorAWS Graviton2 ProcessorAMD EPYC 7R32
Clock Speed2.5 GHz3 GHz
Threads Per Core12
Accelerators
GPUnoyes
GPU NameRadeon Pro V520
GPU ManufacturerAMD
GPUs1
GPU Memory8 GiB
GPU Total Memory8 GiB
Inference Acceleratornono
Accelerator Memory8 GiB
FPGAnono
Instances
Sizesr6g.12xlarge, r6g.16xlarge, r6g.2xlarge, r6g.4xlarge, r6g.8xlarge, r6g.large, r6g.medium, r6g.metal, r6g.xlargeg4ad.16xlarge, g4ad.2xlarge, g4ad.4xlarge, g4ad.8xlarge, g4ad.xlarge
Generationsr6g.2xlarge, r7g.2xlarge, r8g.2xlarge
Variantsr6a.2xlarge, r6gd.2xlarge, r6i.2xlarge, r6id.2xlarge, r6idn.2xlarge, r6in.2xlargeg4dn.2xlarge
SageMakerml.r6g.2xlarge
RDSdb.r6g.2xlarge
DocumentDBdb.r6g.2xlarge
OpenSearchr6g.2xlarge.search
ElastiCachecache.r6g.2xlarge
Free Tiernono
Burstablenono
Hibernationyesno
Instance StorageEBS only300 GB NVMe SSD
EBS (Elastic Block Store)
EBS Optimizeddefaultdefault
Encryptionsupportedsupported
NVMerequiredrequired
Dedicated Throughputup to 4500 MBpsup to 3000 MBps
Optimized Baseline Bandwidth2375 Mbps800 Mbps
Optimized Baseline Throughput296.875 Mbps100 Mbps
Optimized Baseline Performance12000 IOPS3400 IOPS
Optimized Max Performance20000 IOPS13333 IOPS
Optimized Max Bandwidth4750 Mbps3170 Mbps
Optimized Max Throughput593.75 Mbps396.25 Mbps
Networking
Networking PerformanceUp to 10 GigabitUp to 10 Gigabit
Enhanced Networkingyesyes
Max Interfaces42
Max Cards11
IPv4 Addresses per Interface154
IPv6 Addresses per Interface154
IPv6 Supportyesyes
ENA Supportrequiredrequired
EFA Supportnono
Encryption in Transit Supportnoyes
ENA SRD Supportnono
Avg Price Diff1.00x1.32x

Regional Prices

US Dollar ($)
Per Hour
Linux
Shared Tenancy
On Demand
Geography
Region
r6g.2xlarge
g4ad.2xlarge
Asia PacificAsia Pacific (Hyderabad) (ap-south-2)0.2600n/a
Asia PacificAsia Pacific (Mumbai) (ap-south-1)0.2600n/a
HiddenHidden (hidden-1)0.40320.6042
HiddenHidden (hidden-10)0.4480n/a
HiddenHidden (hidden-11)0.4512n/a
HiddenHidden (hidden-12)0.4512n/a
HiddenHidden (hidden-13)0.4720n/a
HiddenHidden (hidden-14)0.4736n/a
HiddenHidden (hidden-15)0.4736n/a
HiddenHidden (hidden-16)0.4738n/a
HiddenHidden (hidden-17)0.4832n/a
HiddenHidden (hidden-18)0.4832n/a
HiddenHidden (hidden-19)0.4832n/a
HiddenHidden (hidden-2)0.40320.6042
HiddenHidden (hidden-20)0.4832n/a
HiddenHidden (hidden-21)0.4864n/a
HiddenHidden (hidden-22)0.4864n/a
HiddenHidden (hidden-23)0.4864n/a
HiddenHidden (hidden-24)0.4864n/a
HiddenHidden (hidden-25)0.4864n/a
HiddenHidden (hidden-26)0.4880n/a
HiddenHidden (hidden-27)0.4963n/a
HiddenHidden (hidden-28)0.4963n/a
HiddenHidden (hidden-29)0.5074n/a
HiddenHidden (hidden-3)0.41340.6329
HiddenHidden (hidden-30)0.5350n/a
HiddenHidden (hidden-31)0.5360n/a
HiddenHidden (hidden-32)0.5376n/a
HiddenHidden (hidden-33)0.6432n/a
HiddenHidden (hidden-4)0.41340.6766
HiddenHidden (hidden-5)0.42340.7303
HiddenHidden (hidden-6)0.4280n/a
HiddenHidden (hidden-7)0.4378n/a
HiddenHidden (hidden-8)0.4416n/a
HiddenHidden (hidden-9)0.4416n/a
USUS East (Ohio) (us-east-2)n/a0.5412
USUS East (Virginia) (us-east-1)0.40320.5412
USUS West (Oregon) (us-west-2)n/a0.5412
Activate subscription to see all regions and unlock all features

Related Comparisons

Other instances worth weighing against these.