NVIDIA A30

The NVIDIA A30 is a data center graphics card based on the Ampere architecture. Released on 2021-04-12 with a launch price of $5,000.00, it features 3584 CUDA cores and 24 GB of HBM2 memory.

A30 GPU

General info about A30

Architecture Ampere (GA100)
Market Segment Data Center
Release Date 2021-04-12
Launch Price $5,000.00
Manufacturing Process 7nm

Technical specs of A30

CUDA Cores 3584
Base Clock Speed 930 MHz
Boost Clock Speed 1440 MHz
Transistor Count 54.2B
VRAM Capacity 24 GB HBM2
Memory Bus Width 3072 bits
Memory Bandwidth 933.0 GB/s
TDP 165 W

Key technical parameters of the NVIDIA A30 include its 3584 CUDA cores, 930 MHz base clock, and 1440 MHz boost clock, delivering high performance for data center applications.

Benchmark performance of A30

FP32 (float) 10.3 TFLOPS
FP16 (half) 165 TFLOPS

The NVIDIA A30 achieves 10.3 TFLOPS in FP32 performance, making it a top contender in data center workloads.

Gaming performance of A30

The NVIDIA A30 is not designed for gaming.

Features and connectivity of A30

Tensor_cores Gen 3
Tf32 True
Mig True
Ports NVLink 3, PCIe Gen4

Physical dimensions of A30

Length 10.5in
Width 4.4in
Height 2-slot

Rankings and efficiency of A30

Ranking Position #15
Popularity Ranking #20
Cost Effectiveness 1.4/5
Power Efficiency 1.5/5

Top GPUs for Training and Inference

Category Rank 1 Rank 2 Rank 3
Best for Training NVIDIA H200 NVIDIA H100 NVIDIA B200
Best for Inference NVIDIA A40 NVIDIA A100 NVIDIA A10
0 of 44 row(s) selected.
Page 1 of 0