c5a.4xlarge vs g5.4xlarge

Instance Typec5a.4xlargeg5.4xlarge
Instance FamilyCompute optimizedGPU instance
DetailsHigh-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
5 – Generation
a – AMD processor
4xlarge – 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)
5 – Generation
4xlarge – Size
vCPUs1616
Memory32 GiB64 GiB
CPU Architecturex86_64x86_64
ProcessorAMD EPYC 7R32AMD EPYC 7R32
Clock Speed3.3 GHz3.3 GHz
Threads Per Core22
Accelerators
GPUnoyes
GPU NameA10G
GPU ManufacturerNVIDIA
GPUs1
GPU Memory22.35 GiB
GPU Total Memory22.35 GiB
Inference Acceleratornono
Accelerator Memory24 GiB
FPGAnono
Instances
Sizesc5a.12xlarge, c5a.16xlarge, c5a.24xlarge, c5a.2xlarge, c5a.4xlarge, c5a.8xlarge, c5a.large, c5a.xlargeg5.12xlarge, g5.16xlarge, g5.24xlarge, g5.2xlarge, g5.48xlarge, g5.4xlarge, g5.8xlarge, g5.xlarge
Generationsc5a.4xlarge, c6a.4xlarge, c7a.4xlarge, c8a.4xlargeg3.4xlarge, g5.4xlarge, g6.4xlarge, g7.4xlarge
Variantsc5.4xlarge, c5ad.4xlarge, c5d.4xlarge, c5n.4xlargeg5g.4xlarge
SageMakerml.g5.4xlarge
Free Tiernono
Burstablenono
Hibernationnono
Instance StorageEBS only1 x 600 GB NVMe SSD
EBS (Elastic Block Store)
EBS Optimizeddefaultdefault
Encryptionsupportedsupported
NVMerequiredrequired
Dedicated Throughputup to 3170 MBps8000 MBps
Optimized Baseline Bandwidth1580 Mbps4750 Mbps
Optimized Baseline Throughput197.5 Mbps593.75 Mbps
Optimized Baseline Performance6600 IOPS20000 IOPS
Optimized Max Performance13300 IOPS20000 IOPS
Optimized Max Bandwidth3170 Mbps4750 Mbps
Optimized Max Throughput396.25 Mbps593.75 Mbps
Networking
Networking PerformanceUp to 10 GigabitUp to 25 Gigabit
Enhanced Networkingyesyes
Max Interfaces88
Max Cards11
IPv4 Addresses per Interface3030
IPv6 Addresses per Interface3030
IPv6 Supportyesyes
ENA Supportrequiredrequired
EFA Supportnono
Encryption in Transit Supportyesyes
ENA SRD Supportnono
Avg Price Diff1.00x2.81x

Regional Prices

US Dollar ($)
Per Hour
Linux
Shared Tenancy
On Demand
Geography
Region
c5a.4xlarge
g5.4xlarge
Asia PacificAsia Pacific (Mumbai) (ap-south-1)0.3760n/a
HiddenHidden (hidden-1)0.61601.7112
HiddenHidden (hidden-10)0.72802.0615
HiddenHidden (hidden-11)0.73602.0615
HiddenHidden (hidden-12)0.73602.1115
HiddenHidden (hidden-13)0.76002.2730
HiddenHidden (hidden-14)0.76002.3553
HiddenHidden (hidden-15)0.76802.5003
HiddenHidden (hidden-16)0.77602.7605
HiddenHidden (hidden-17)0.8000n/a
HiddenHidden (hidden-18)0.8240n/a
HiddenHidden (hidden-19)0.9440n/a
HiddenHidden (hidden-2)0.65601.7225
HiddenHidden (hidden-3)0.67201.8032
HiddenHidden (hidden-4)0.68801.8129
HiddenHidden (hidden-5)0.68801.9035
HiddenHidden (hidden-6)0.69601.9501
HiddenHidden (hidden-7)0.70401.9921
HiddenHidden (hidden-8)0.72801.9969
HiddenHidden (hidden-9)0.72802.0308
USUS East (Ohio) (us-east-2)0.61601.6240
USUS East (Virginia) (us-east-1)0.61601.6240
USUS West (Oregon) (us-west-2)n/a1.6240
Activate subscription to see all regions and unlock all features

Related Comparisons

Other instances worth weighing against these.