GPU catalogue · AWS

AWS Inferentia2

Amazon's inference silicon.

32 GB GPU memory Accelerator

Request GPU

AWS Inferentia2

Specifications

AWS Inferentia2: public facts

Good for: Cheap serving on AWS with Neuron.

Machine	AWS Inferentia2
Memory	32 GB HBM
Architecture	Inferentia2

Models

Which models fit the AWS Inferentia2

language models · image models · video models · embedding models.

Explore

More

GPU catalogue AxForge GPU offerings Model catalogue → On the forum → Pricing →

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms