inf2.xlarge by Amazon Web Services

Go back to list

Main description
Service Elastic Compute Cloud
Machine type Virtual machine
Category AI
Release date N/A
Specifications
CPU 4
CPU architecture arm64
RAM 16.0 GB (16384MB)
GPU None
Root volume size Flexible
Extra volume size None
Extra volume size #2 None
Extra
Max bandwidth 15000 Mbps
Included traffic 0 GB/month
Deprecated False

Inferentia 2

High performance at the lowest cost in Amazon EC2 for generative AI inference