inf2.24xlarge

The inf2.24xlarge instance is in the machine learning asic instances family with 96 vCPUs, 384.0 GiB of memory and 50 Gibps of bandwidth starting at $6.49063 per hour.

paid

Pricing

On Demand

Spot

1 Yr Reserved

3 Yr Reserved

$2046.88 per month (-57%) with Autopilot

dns

Family Sizes

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

Instance Variants

Variant
inf1
inf2
info

Instance Details

Compute Value
vCPUs 96
Memory (GiB) 384.0
Memory per vCPU (GiB) 4.0
Physical Processor AMD EPYC 7R13 Processor
Clock Speed (GHz) 2.95
CPU Architecture x86_64
GPU 6
GPU Architecture AWS Inferentia2
Video Memory (GiB) 192
GPU Compute Capability (?) 0
FPGA 0
Networking Value
Network Performance (Gibps) 50
Enhanced Networking True
IPV6 True
Placement Group (?) True
Storage Value
EBS Optimized True
Max Bandwidth (Mbps) on (EBS) 30000
Max Throughput (MB/s) on EBS 3750.0
Max I/O Operations/second (IOPS) 120000
Baseline Bandwidth (Mbps) on (EBS) 30000
Baseline Throughput (MB/s) on EBS 3750.0
Baseline I/O Operations/second (IOPS) 120000
Amazon Value
Generation current
Instance Type inf2.24xlarge
Family Machine Learning ASIC Instances
Name INF2 24xlarge
Elastic Map Reduce (EMR) False

close