Optimize Kubernetes Costs with pod efficiency reports ->

inf2.8xlarge

The inf2.8xlarge instance is in the machine learning asic instances family with 32 vCPUs, 128.0 GiB of memory and up to 25 Gibps of bandwidth starting at $1.96786 per hour.

paid

Pricing

On Demand

Spot

1 Yr Reserved

3 Yr Reserved

$620.59 per month (-57%) with Autopilot

Learn more

dns

Family Sizes

Size	vCPUs	Memory (GiB)
inf2.xlarge	4	16
inf2.8xlarge	32	128
inf2.24xlarge	96	384
inf2.48xlarge	192	768

Compare inf2.8xlarge to other Instances

dns

Instance Variants

Variant
inf1
inf2

info

Instance Details

Compute	Value
vCPUs	32
Memory (GiB)	128.0
Memory per vCPU (GiB)	4.0
Physical Processor	AMD EPYC 7R13 Processor
Clock Speed (GHz)	2.95
CPU Architecture	x86_64
GPU	1
GPU Architecture	AWS Inferentia2
Video Memory (GiB)	32
GPU Compute Capability (?)	0
FPGA	0

Networking	Value
Network Performance (Gibps)	Up to 25
Enhanced Networking	True
IPV6	True
Placement Group (?)	True

Storage	Value
EBS Optimized	True
Max Bandwidth (Mbps) on (EBS)	10000
Max Throughput (MB/s) on EBS	1250.0
Max I/O Operations/second (IOPS)	40000
Baseline Bandwidth (Mbps) on (EBS)	10000
Baseline Throughput (MB/s) on EBS	1250.0
Baseline I/O Operations/second (IOPS)	40000

Amazon	Value
Generation	current
Instance Type	inf2.8xlarge
Family	Machine Learning ASIC Instances
Name	INF2 Eight Extra Large
Elastic Map Reduce (EMR)	False

EC2 Rightsizing Recommendations

Connect your AWS account with Vantage to see a savings estimate.