Compare GCP Instances

Instance Type	n4d-highmem-2	a2-highgpu-2g
Details	High-performance web servers, scientific modeling, batch processing, distributed analytics, HPC, machine/deep learning inference, ad serving, scalable multiplayer gaming, and video encoding. n – General purpose 4 – Generation highmem – 8x RAM/CPU ratio 2 – Number of CPUs	Optimized for accelerated high performance computing workloads. a – Accelerator optimized 2 – Generation highgpu – High amound of GPU memory - 40x RAM/GPU ratio 2g – Number of GPUs
Instance Family	General-purpose	Accelerator optimized
Description	2 vCPUs, 16 GB RAM	Accelerator Optimized: 2 NVIDIA Tesla A100 GPUs, 24 vCPUs, 170GB RAM
vCPUs	2	24
Memory	16 GiB	170 GiB
CPU Architecture	x86_64	x86_64
Processor	AMD EPYC Turin	Intel Cascade Lake
Shared CPU	no	no
GPU	no	yes
GPUs		2
GPU Name		nvidia-tesla-a100
GPU Total RAM (GiB)		170
Sustained Discounts (SUDs)	no	no
Extended Memory	yes
Sole Tenancy	no	yes
Nested Virtualization	no	yes
Custom Shapes	yes	no
Confidential Compute	no	no
Maximum Persistent Disks	128	128
Maximum Persistent Disks Size	263168 GB	263168 GB
Disk Interface Type	NVMe	SCSI (PD, Local SSD) NVMe (Local SSD)
Local SSD	no	yes
Max Local SSD		3000 GB
Extreme Persistent Disks	no	no
Hyperdisk Extreme	no	no
Hyperdisk Throughput	yes	no
Network Interfaces	gVNIC	gVNIC, VirtIO-Net
Avg Price Diff	1.00x	66.43x

Regional Prices

Geography	Region	n4d-highmem-2	a2-highgpu-2g
Hidden	Hidden (hidden-1)	0.1112	7.4959
Hidden	Hidden (hidden-10)	0.1371	n/a
Hidden	Hidden (hidden-2)	0.1112	7.8687
Hidden	Hidden (hidden-3)	0.1112	8.0275
Hidden	Hidden (hidden-4)	0.1168	8.0814
Hidden	Hidden (hidden-5)	0.1223	8.0992
Hidden	Hidden (hidden-6)	0.1253	8.0992
Hidden	Hidden (hidden-7)	0.1267	8.6501
Hidden	Hidden (hidden-8)	0.1313	n/a
Hidden	Hidden (hidden-9)	0.1337	n/a
APAC	India (asia-south1)	0.0846	n/a
North America	Iowa (us-central1)	0.1112	7.3468
North America	Oregon (us-west1)	n/a	7.3468
North America	South Carolina (us-east1)	0.1112	7.3468