g4ad.2xlarge vs r8in.2xlarge

Instance Typeg4ad.2xlarger8in.2xlarge
Instance FamilyGPU instanceMemory optimized
DetailsMachine 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
High-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
8 – Generation
i – Intel processor
n – Network and EBS optimized
2xlarge – Size
vCPUs88
Memory32 GiB64 GiB
CPU Architecturex86_64x86_64
ProcessorAMD EPYC 7R32Intel Xeon Scalable (Granite Rapids)
Clock Speed3 GHz3.9 GHz
Threads Per Core22
Accelerators
GPUyesno
GPU NameRadeon Pro V520
GPU ManufacturerAMD
GPUs1
GPU Memory8 GiB
GPU Total Memory8 GiB
Inference Acceleratornono
Accelerator Memory8 GiB
FPGAnono
Instances
Sizesg4ad.16xlarge, g4ad.2xlarge, g4ad.4xlarge, g4ad.8xlarge, g4ad.xlarger8in.12xlarge, r8in.16xlarge, r8in.24xlarge, r8in.2xlarge, r8in.32xlarge, r8in.48xlarge, r8in.4xlarge, r8in.8xlarge, r8in.96xlarge, r8in.large, r8in.metal-48xl, r8in.metal-96xl, r8in.xlarge
Generationsr6in.2xlarge, r8in.2xlarge
Variantsg4dn.2xlarger8a.2xlarge, r8g.2xlarge, r8gb.2xlarge, r8gd.2xlarge, r8gn.2xlarge, r8i-flex.2xlarge, r8i.2xlarge, r8ib.2xlarge, r8id.2xlarge, r8idb.2xlarge, r8idn.2xlarge
Free Tiernono
Burstablenono
Hibernationnoyes
Instance Storage300 GB NVMe SSDEBS only
EBS (Elastic Block Store)
EBS Optimizeddefaultdefault
Encryptionsupportedsupported
NVMerequiredrequired
Dedicated Throughputup to 3000 MBpsup to 10000 MBps
Optimized Baseline Bandwidth800 Mbps2500 Mbps
Optimized Baseline Throughput100 Mbps312.5 Mbps
Optimized Baseline Performance3400 IOPS12000 IOPS
Optimized Max Performance13333 IOPS40000 IOPS
Optimized Max Bandwidth3170 Mbps10000 Mbps
Optimized Max Throughput396.25 Mbps1250 Mbps
Networking
Networking PerformanceUp to 10 GigabitUp to 40 Gigabit
Enhanced Networkingyesyes
Max Interfaces24
Max Cards11
IPv4 Addresses per Interface430
IPv6 Addresses per Interface430
IPv6 Supportyesyes
ENA Supportrequiredrequired
EFA Supportnono
Encryption in Transit Supportyesyes
ENA SRD Supportnono
Avg Price Diff1.00x1.50x

Regional Prices

US Dollar ($)
Per Hour
Linux
Shared Tenancy
On Demand
Geography
Region
g4ad.2xlarge
r8in.2xlarge
HiddenHidden (hidden-1)0.60420.9379
HiddenHidden (hidden-2)0.60420.9379
HiddenHidden (hidden-3)0.63290.9996
HiddenHidden (hidden-4)0.67661.0165
HiddenHidden (hidden-5)0.7303n/a
USUS East (Ohio) (us-east-2)0.54120.8368
USUS East (Virginia) (us-east-1)0.54120.8368
USUS West (Oregon) (us-west-2)0.54120.8368
Activate subscription to see all regions and unlock all features

Related Comparisons

Other instances worth weighing against these.