Vantage is the FinOps platform your engineering team will actually use. Get a demo.

p3.8xlarge

The p3.8xlarge instance is in the GPU instance family with 32 vCPUs, 244 GiB of memory and 10 Gibps of bandwidth starting at $12.24 per hour.

Pricing

$12.24

On Demand

$1.7136

Spot

N/A

1-Year Reserved

N/A

3-Year Reserved

Request a demo

Family Sizes

SizevCPUsMemory (GiB)
p3.2xlarge861
p3.8xlarge32244
p3.16xlarge64488

Compare p3.8xlarge to other instances

Instance Variants

Variant
p3
p3dn

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)244
Memory per vCPU (GiB)7.63
Physical ProcessorIntel Xeon E5-2686 v4 (Broadwell)
Clock Speed (GHz)2.3 GHz
CPU Architecturex86_64
GPU
4
GPU Architecture
NVIDIA Tesla V100
Video Memory (GiB)64
GPU Compute Capability ?7
FPGA
0
NetworkingValue
Network Performance (Gibps)10
Enhanced Networking
true
IPv6
true
Placement Group ?
StorageValue
EBS Optimized
true
Max Bandwidth (Mbps) on EBS7000
Max Throughput (MB/s) on EBS875
Max I/O operations/second IOPS40000
Baseline Bandwidth (Mbps) on EBS7000
Baseline Throughput (MB/s) on EBS875
Baseline I/O operations/second IOPS40000
Devices0
Swap Partition
false
NVME Drive ?
false
Disk Space (GiB)0
SSD
false
Initialize Storage
false
AmazonValue
Generation
current
Instance Typep3.8xlarge
FamilyGPU instance
NameP3 High Performance GPU Eight Extra Large
Elastic Map Reduce EMR
true
The Vantage MCP Server: Use AI to Analyze Your Cost and Usage Data

Ask questions about your organization's previous and current cloud cost spend, cost tagging, provider integrations, and more.

EC2 GPU Instances

EC2 GPU instances have been hugely popular due to advances in machine learning, gaming, etc. However, it can be difficult to know which to choose.

How AWS is Using Capacity Blocks to Alleviate the GPU Shortage

Capacity Blocks provide greater availability and cost savings for short-term GPU needs.

DocsBy Vantage