inf2.8xlarge

The inf2.8xlarge instance is in the Machine Learning ASIC Instances family with 32 vCPUs, 128 GiB of memory and up to 25 Gibps of bandwidth starting at $1.96786 per hour.

Pricing

$1.9679

On Demand

$0.5904

Spot

$1.2397

1-Year Reserved

$0.8501

3-Year Reserved

Request a demo

Family Sizes

SizevCPUsMemory (GiB)
inf2.xlarge416
inf2.8xlarge32128
inf2.24xlarge96384
inf2.48xlarge192768

Instance Variants

Variant
inf1
inf2

Having trouble making sense of your EC2 costs? Check out cur.vantage.sh for an AWS billing code lookup tool.

Instance Details

ComputeValue
vCPUs32
Memory (GiB)128
Memory per vCPU (GiB)4
Physical ProcessorAMD EPYC 7R13 Processor
Clock Speed (GHz)2.95 GHz
CPU Architecturex86_64
GPU
1
GPU Architecture
AWS Inferentia2
Video Memory (GiB)32
GPU Compute Capability (?)0
FPGA
0
NetworkingValue
Network Performance (Gibps)up to 25
Enhanced Networking
true
IPv6
true
Placement Group (?)
StorageValue
EBS Optimized
true
Max Bandwidth (Mbps) on (EBS)10000
Max Throughput (MB/s) on (EBS)1250
Max I/O operations/second (IOPS)40000
Baseline Bandwidth (Mbps) on (EBS)10000
Baseline Throughput (MB/s) on (EBS)1250
Baseline I/O operations/second (IOPS)40000
Devices0
Swap Partition
false
NVME Drive (?)
false
Disk Space (GiB)0
SSD
false
Initialize Storage
false
AmazonValue
Generation
current
Instance Typeinf2.8xlarge
FamilyMachine Learning ASIC Instances
NameINF2 Eight Extra Large
Elastic Map Reduce (EMR)
false
DocsBy Vantage