Nvidia A16 vs Nvidia RTX 3070

A data center GPU against a consumer card on the Ampere architecture: 16 GB GDDR6 against 8 GB GDDR6 and 2.2x the memory bandwidth on the RTX 3070.

At a glance

Updated 6 minutes ago

Nvidia A16

Nvidia RTX 3070

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

Billing	A16	RTX 3070	Difference
On-demand	$0.47	$0.08	6.2x more expensive on A16
Spot	No spot listings	$0.04
Reserved	No reserved listings	$0.11
Median	$0.56	$0.11	5x more expensive on A16

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	A16	RTX 3070	Difference
Memory
Capacity	16 GB GDDR6	8 GB GDDR6	2x more on A16
Bandwidth	200 GB/s	448 GB/s	2.2x higher on RTX 3070
Bus width	128-bit	256-bit	2x wider on RTX 3070
Compute · dense
FP16 / BF16	17.9 TFLOPS	40.6 TFLOPS	2.3x higher on RTX 3070
INT8	35.9 TOPS	162.6 TOPS	4.5x higher on RTX 3070
FP32	4.5 TFLOPS	20.3 TFLOPS	4.5x higher on RTX 3070
Platform
Interconnect	PCIe only	PCIe only
Released	Q2 2021	Q4 2020
Precision
Supported formats	FP16BF16TF32FP32INT4INT8	FP16BF16TF32FP32INT4INT8

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.