Nvidia A30 vs Nvidia GTX 1660 Super

A data center GPU against a consumer card, one Ampere and one Turing: 24 GB HBM2 against 6 GB GDDR6 and 2.8x the memory bandwidth on the A30.

At a glance

Updated 7 minutes ago

Nvidia A30

Nvidia GTX 1660 Super

Cheapest listed price per GPU per hour by billing type, and the median across providers.

Billing	A30	GTX 1660 Super	Difference
On-demand	$0.29	$0.04	7.2x more expensive on A30
Spot	No spot listings	$0.02
Reserved	$0.43	$0.07	6.4x more expensive on A30
Median	$0.55	$0.04	14x more expensive on A30

Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Spec	A30	GTX 1660 Super	Difference
Memory
Capacity	24 GB HBM2	6 GB GDDR6	4x more on A30
Bandwidth	933 GB/s	336 GB/s	2.8x higher on A30
Bus width		192-bit
Compute · dense
FP16 / BF16	165 TFLOPS	10.1 TFLOPS	16x higher on A30
INT8	330 TOPS	Not supported	A30 only
FP32	10.3 TFLOPS	5.0 TFLOPS	2x higher on A30
FP64	5.2 TFLOPS	Not supported	A30 only
Platform
Interconnect	PCIe only	PCIe only
Board power	165 W	125 W	1.3x higher on A30
Released	Q2 2021	Q4 2019	17 months newer on A30
Precision
Supported formats	FP16BF16TF32FP32FP64INT4INT8	FP16FP32

Compute: Vendor peak figures, dense and per GPU. Not measured throughput.

Providers listing these GPUs, those with both first, so you can switch without moving clouds.