g5g.16xlarge vs g7.12xlarge

Instance Typeg5g.16xlargeg7.12xlarge
Instance FamilyGPU instanceGPU instance
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)
5 – Generation
g – AWS Graviton processor
16xlarge – 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)
7 – Generation
12xlarge – Size
vCPUs6448
Memory128 GiB192 GiB
CPU Architecturearm64x86_64
ProcessorAWS Graviton2 ProcessorIntel Xeon Scalable (Granite Rapids)
Clock Speed2.5 GHz3.9 GHz
Threads Per Core11
Accelerators
GPUyesyes
GPU NameT4gRTX PRO 4500
GPU ManufacturerNVIDIANVIDIA
GPUs22
GPU Memory16 GiB32 GiB
GPU Total Memory32 GiB64 GiB
Inference Acceleratornono
Accelerator Memory32 GiB64 GiB
FPGAnono
Instances
Sizesg5g.16xlarge, g5g.2xlarge, g5g.4xlarge, g5g.8xlarge, g5g.metal, g5g.xlargeg7.12xlarge, g7.24xlarge, g7.2xlarge, g7.48xlarge, g7.4xlarge, g7.8xlarge
Generationsg5.12xlarge, g6.12xlarge, g7.12xlarge
Variantsg5.16xlargeg7e.12xlarge
SageMakerml.g7.12xlarge
Free Tiernono
Burstablenono
Hibernationnono
Instance StorageEBS only1x1900 GB NVMe SSD
EBS (Elastic Block Store)
EBS Optimizeddefaultdefault
Encryptionsupportedsupported
NVMerequiredrequired
Dedicated Throughput19000 MBps20000 MBps
Optimized Baseline Bandwidth19000 Mbps20000 Mbps
Optimized Baseline Throughput2375 Mbps2500 Mbps
Optimized Baseline Performance80000 IOPS80000 IOPS
Optimized Max Performance80000 IOPS80000 IOPS
Optimized Max Bandwidth19000 Mbps20000 Mbps
Optimized Max Throughput2375 Mbps2500 Mbps
Networking
Networking Performance25 Gigabit175 Gigabit
Enhanced Networkingyesyes
Max Interfaces1512
Max Cards11
IPv4 Addresses per Interface5064
IPv6 Addresses per Interface5064
IPv6 Supportyesyes
ENA Supportrequiredrequired
EFA Supportnoyes
EFA Max Interfaces1
Encryption in Transit Supportnoyes
ENA SRD Supportnono
Avg Price Diff1.00x2.21x

Regional Prices

US Dollar ($)
Per Hour
Linux
Shared Tenancy
On Demand
Geography
Region
g5g.16xlarge
g7.12xlarge
EuropeEurope (Spain) (eu-south-2)3.0622n/a
HiddenHidden (hidden-1)3.37527.4847
HiddenHidden (hidden-2)3.4326n/a
HiddenHidden (hidden-3)3.7039n/a
HiddenHidden (hidden-4)3.8395n/a
USUS East (Ohio) (us-east-2)n/a7.1283
USUS East (Virginia) (us-east-1)2.74407.1283
USUS West (Oregon) (us-west-2)2.74407.1283
Activate subscription to see all regions and unlock all features  

Related Comparisons

Other instances worth weighing against these.