inf1.2xlarge vs r6in.2xlarge

Instance Typeinf1.2xlarger6in.2xlarge
Instance FamilyMachine Learning ASICMemory optimized
DetailsMachine Learning (ML) inference

inf – AWS Inferentia
1 – Generation
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
6 – Generation
i – Intel processor
n – Network and EBS optimized
2xlarge – Size
vCPUs88
Memory16 GiB64 GiB
CPU Architecturex86_64x86_64
ProcessorIntel Xeon Platinum 8275CL (Cascade Lake)Intel Xeon 8375C (Ice Lake)
Clock Speed2.5 GHz3.5 GHz
Threads Per Core22
Accelerators
GPUnono
GPUs1
Inference Acceleratoryesno
Inference Accelerator NameInferentia
Inference Accelerator ManufacturerAWS
Inference Accelerator Count1
FPGAnono
Instances
Sizesinf1.24xlarge, inf1.2xlarge, inf1.6xlarge, inf1.xlarger6in.12xlarge, r6in.16xlarge, r6in.24xlarge, r6in.2xlarge, r6in.32xlarge, r6in.4xlarge, r6in.8xlarge, r6in.large, r6in.metal, r6in.xlarge
Generationsr6in.2xlarge, r8in.2xlarge
Variantsr6a.2xlarge, r6g.2xlarge, r6gd.2xlarge, r6i.2xlarge, r6id.2xlarge, r6idn.2xlarge
SageMakerml.inf1.2xlarge
RDSdb.r6in.2xlarge
Free Tiernono
Burstablenono
Hibernationnoyes
Instance StorageEBS onlyEBS only
EBS (Elastic Block Store)
EBS Optimizeddefaultdefault
Encryptionsupportedsupported
NVMerequiredrequired
Dedicated Throughput875 MBpsup to 25000 MBps
Optimized Baseline Bandwidth1190 Mbps6250 Mbps
Optimized Baseline Throughput148.75 Mbps781.25 Mbps
Optimized Baseline Performance6000 IOPS25000 IOPS
Optimized Max Performance20000 IOPS100000 IOPS
Optimized Max Bandwidth4750 Mbps25000 Mbps
Optimized Max Throughput593.75 Mbps3125 Mbps
Networking
Networking PerformanceUp to 25 GigabitUp to 40000 Megabit
Enhanced Networkingnoyes
Max Interfaces44
Max Cards11
IPv4 Addresses per Interface1015
IPv6 Addresses per Interface1015
IPv6 Supportyesyes
ENA Supportrequiredrequired
EFA Supportnono
Encryption in Transit Supportyesyes
ENA SRD Supportnono
Avg Price Diff1.00x1.79x

Regional Prices

US Dollar ($)
Per Hour
Linux
Shared Tenancy
On Demand
Geography
Region
inf1.2xlarge
r6in.2xlarge
HiddenHidden (hidden-1)0.38100.7441
HiddenHidden (hidden-10)0.4460n/a
HiddenHidden (hidden-11)0.4530n/a
HiddenHidden (hidden-12)0.4530n/a
HiddenHidden (hidden-13)0.4560n/a
HiddenHidden (hidden-14)0.4560n/a
HiddenHidden (hidden-15)0.4890n/a
HiddenHidden (hidden-16)0.4890n/a
HiddenHidden (hidden-17)0.5580n/a
HiddenHidden (hidden-18)0.5980n/a
HiddenHidden (hidden-2)0.38500.7628
HiddenHidden (hidden-3)0.40300.7816
HiddenHidden (hidden-4)0.40300.8190
HiddenHidden (hidden-5)0.42300.8330
HiddenHidden (hidden-6)0.42400.8330
HiddenHidden (hidden-7)0.42400.8377
HiddenHidden (hidden-8)0.43500.8471
HiddenHidden (hidden-9)0.44400.8471
USUS East (Ohio) (us-east-2)0.36200.6973
USUS East (Virginia) (us-east-1)0.36200.6973
USUS West (Oregon) (us-west-2)0.36200.6973
Activate subscription to see all regions and unlock all features

Related Comparisons

Other instances worth weighing against these.