Nvidia A100 vs Nvidia GTX 1660

The A100 is newer, with 13x the memory and 10x the bandwidth. The GTX 1660 is cheaper right now.

At a glance

Memory

13x more on A100

A100: 80 GB

GTX 1660: 6 GB

Memory bandwidth

10x higher on A100

A100: 1,935 GB/s

GTX 1660: 192 GB/s

Cheapest on-demand

89% cheaper on GTX 1660

A100: $0.37 /GPU/hr

GTX 1660: $0.04 /GPU/hr

Price comparison

Median price per GPU per hour by billing type, with the cheapest listing under it.

Billing	A100	GTX 1660
On-demand	$1.77 /GPU/hr from $0.37	-- /GPU/hr from $0.04
Reserved	$1.43 /GPU/hr from $0.36 (3 mo)	-- /GPU/hr from $0.19 (24 mo)
Spot	$0.96 /GPU/hr from $0.23	-- /GPU/hr from $0.02

Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. No median for on-demand, reserved and spot on the GTX 1660: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.

Price history

A100 vs GTX 1660 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	A100	GTX 1660	Difference
Memory
Capacity	80 GB HBM2e 40 GB on SXM, PCIe	6 GB GDDR5	13x more on A100
Bandwidth	1,935 GB/s 2,039 GB/s on SXM 1,555 GB/s on SXM, PCIe	192 GB/s	10x higher on A100
Bus width	5,120-bit	192-bit	27x wider on A100
Compute · dense
FP16 / BF16	312 TFLOPS	10.1 TFLOPS	31x higher on A100
INT8	624 TOPS	Not supported	A100 only
FP32	19.5 TFLOPS	5.0 TFLOPS	3.9x higher on A100
FP64	9.7 TFLOPS	Not supported	A100 only
Platform
Interconnect	NVLink 600 GB/s	PCIe only	NVLink on A100 only
Board power	300 W	120 W	2.5x higher on A100
Released	Q2 2020	Q1 2019	14 months newer on A100
Precision
Supported formats	FP16BF16TF32FP32FP64INT4INT8	FP16FP32

Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.

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

Source: A100 datasheet and GTX 1660 datasheet.

Where to rent them

Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.

Provider	A100	GTX 1660
Vast.ai USA	$0.40 /GPU/hr On-demand SXM	$0.0489 /GPU/hr On-demand
GPU.ai UAE	$0.37 /GPU/hr On-demand	--
Jarvislabs India	$0.89 /GPU/hr On-demand	--
Runpod USA	$1.00 /GPU/hr On-demand SXM	--
Lium Distributed	$1.01 /GPU/hr On-demand SXM	--
Thunder Compute USA	$1.09 /GPU/hr On-demand	--
Massed Compute USA	$1.35 /GPU/hr On-demand	--
Packet·ai USA	$1.43 /GPU/hr On-demand	--
Salad Distributed	--	$0.0400 /GPU/hr On-demand
Database Mart USA	--	$0.19 /GPU/hr Reserved