c8a.xlarge vs x8g.xlarge

Accelerators
Instance Type	c8a.xlarge	x8g.xlarge
Instance Family	Compute optimized	Memory optimized
Details	High-performance web servers, scientific modeling, batch processing, distributed analytics, HPC, machine/deep learning inference, ad serving, scalable multiplayer gaming, and video encoding. c – Compute optimized 8 – Generation a – AMD processor xlarge – Size	In-memory databases (like SAP HANA), big data engines (such as Apache Spark, Presto), high-performance computing (HPC), and memory-heavy enterprise apps. x – Extreme RAM / memory intensive 8 – Generation g – AWS Graviton processor xlarge – Size
vCPUs	4	4
Memory	8 GiB	64 GiB
CPU Architecture	x86_64	arm64
Processor	AMD EPYC 9R45 Processor	AWS Graviton4 Processor
Clock Speed	4.5 GHz	2.8 GHz
Threads Per Core	1	1
GPU	no	no
Inference Accelerator	no	no
FPGA	no	no
Instances
Sizes	c8a.12xlarge, c8a.16xlarge, c8a.24xlarge, c8a.2xlarge, c8a.48xlarge, c8a.4xlarge, c8a.8xlarge, c8a.large, c8a.medium, c8a.metal-24xl, c8a.metal-48xl, c8a.xlarge	x8g.12xlarge, x8g.16xlarge, x8g.24xlarge, x8g.2xlarge, x8g.48xlarge, x8g.4xlarge, x8g.8xlarge, x8g.large, x8g.medium, x8g.metal-24xl, x8g.metal-48xl, x8g.xlarge
Generations	c5a.xlarge, c6a.xlarge, c7a.xlarge, c8a.xlarge
Variants	c8g.xlarge, c8gb.xlarge, c8gd.xlarge, c8gn.xlarge, c8i-flex.xlarge, c8i.xlarge, c8ib.xlarge, c8id.xlarge, c8in.xlarge, c8ine.xlarge	x8aedz.xlarge, x8i.xlarge
Free Tier	no	no
Burstable	no	no
Hibernation	yes	no
Instance Storage	EBS only	EBS only
EBS (Elastic Block Store)
EBS Optimized	default	default
Encryption	supported	supported
NVMe	required	required
Dedicated Throughput	up to 10000 MBps	up to 10240 MBps
Optimized Baseline Bandwidth	1250 Mbps	1250 Mbps
Optimized Baseline Throughput	156.25 Mbps	156.25 Mbps
Optimized Baseline Performance	6000 IOPS	6000 IOPS
Optimized Max Performance	40000 IOPS	40000 IOPS
Optimized Max Bandwidth	10000 Mbps	10000 Mbps
Optimized Max Throughput	1250 Mbps	1250 Mbps
Networking
Networking Performance	Up to 15000 Megabit	Up to 12.5 Gigabit
Enhanced Networking	yes	yes
Max Interfaces	4	4
Max Cards	1	1
IPv4 Addresses per Interface	20	15
IPv6 Addresses per Interface	20	15
IPv6 Support	yes	yes
ENA Support	required	required
EFA Support	no	no
Encryption in Transit Support	yes	yes
ENA SRD Support	no	no
Avg Price Diff	1.00x	1.91x

Regional Prices

US Dollar ($)

Per Hour

Linux

Shared Tenancy

On Demand

Geography	Region	c8a.xlarge	x8g.xlarge
Hidden	Hidden (hidden-1)	0.2312	0.4449
Hidden	Hidden (hidden-2)	0.2313	0.4680
Hidden	Hidden (hidden-3)	0.2460	0.4690
Hidden	Hidden (hidden-4)	0.2713	0.5462
US	US East (Ohio) (us-east-2)	0.2155	0.3908
US	US East (Virginia) (us-east-1)	0.2155	0.3908
US	US West (Oregon) (us-west-2)	0.2155	0.3908