NVIDIA A30

NVIDIA · Ampere

Shipping inferenceavailablemid-range
Memory
24GB HBM2
FP8 TFLOPS
N/A
Power
165W
Released
Apr 1, 2021

Technical Specifications

ManufacturerNVIDIA
ArchitectureAmpere
Memory24GB HBM2
Memory Bandwidth0.933 TB/s
FP16 TFLOPS165
FP8 TFLOPSN/A
InterconnectNVLink3 (600GB/s)
Power (TDP)165W
ReleasedApr 1, 2021
StatusShipping

Availability

Available — mainstream inference GPU, lower cost than A100