AWS Inferentia2

Inferentia Gen2 Architecture

Active

Launched November 2022

Core Specifications

VendorAWS
ArchitectureInferentia Gen2
Form Factor
VRAM32 GB
Memory Bandwidth
TDP150 W

Compute Performance

PrecisionTFLOPs
BF16190

Pricing

Cloud Rental (OPEX)

ProviderInstance TypePrice per HourRegionAs of
AWSinf2.48xlarge (12x Inferentia2)$6.49/hrus-east-1Oct 2024
AWSinf2.48xlarge (12x Inferentia2)$6.49/hrus-east-1Oct 2024

Quick Stats

Peak Performance
190
TFLOPs (BF16)
Efficiency
1.27
TFLOPs per Watt

Similar XPUs

View other AWS GPUs or compare across vendors