Star
Optimize Kubernetes clusters with Pod Efficiency Metrics ->
Slack
Star

p3dn.24xlarge

The p3dn.24xlarge instance is in the gpu instance family with 96 vCPUs, 768.0 GiB of memory and 100 Gibps of bandwidth starting at $31.212 per hour.

paid

Pricing

On Demand

Spot

1 Yr Reserved

3 Yr Reserved

$7603.68 per month (-67%) with Autopilot

Learn more
dns

Family Sizes

Size vCPUs Memory (GiB)
p3dn.24xlarge 96 768
dns

Instance Variants

Variant
p3
p3dn
info

Instance Details

Compute Value
vCPUs 96
Memory (GiB) 768.0
Memory per vCPU (GiB) 8.0
Physical Processor Intel Xeon Platinum 8175 (Skylake)
Clock Speed (GHz) 2.5
CPU Architecture x86_64
GPU 8
GPU Architecture NVIDIA Tesla V100
Video Memory (GiB) 256
GPU Compute Capability (?) 7.0
FPGA 0
Networking Value
Network Performance (Gibps) 100
Enhanced Networking True
IPV6 True
Placement Group (?) True
Storage Value
EBS Optimized True
Max Bandwidth (Mbps) on (EBS) 19000
Max Throughput (MB/s) on EBS 2375.0
Max I/O Operations/second (IOPS) 80000
Baseline Bandwidth (Mbps) on (EBS) 19000
Baseline Throughput (MB/s) on EBS 2375.0
Baseline I/O Operations/second (IOPS) 80000
Devices 2
Swap Partition False
NVME Drive True
Disk Space (GiB) 900
SSD True
Initialize Storage False
Amazon Value
Generation current
Instance Type p3dn.24xlarge
Family GPU instance
Name P3DN 24xlarge
Elastic Map Reduce (EMR) False

See a data problem? Open a ticket.



Meet us at re:Invent 2023