GPU catalogue · NVIDIA

NVIDIA A30

Ampere inference card with HBM.

24 GB GPU memory GPU

Request GPU

NVIDIA A30

Specifications

NVIDIA A30: public facts

Good for: Throughput inference of small models.

Machine	NVIDIA A30
Memory	24 GB HBM2
Architecture	Ampere

Models

Which models fit the NVIDIA A30

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