Nvidia A16 vs Nvidia K620

The A16 is newer, with 8x the memory and 6.9x the bandwidth.

At a glance

Memory

8x more on A16

A16: 16 GB

K620: 2 GB

Memory bandwidth

6.9x higher on A16

A16: 200 GB/s

K620: 29 GB/s

Cheapest on-demand

A16: $0.11 /GPU/hr

K620: --

Price comparison

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

Billing	A16	K620	Difference
On-demand	-- /GPU/hr from $0.11	No on-demand listings
Spot	-- /GPU/hr from $0.07	No spot listings

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 and spot on the A16: 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

A16 vs K620 price history

Weekly median on-demand price per GPU per hour

Last 17 months

Aggregating historical prices...

Specs comparison

Spec	A16	K620	Difference
Memory
Capacity	16 GB GDDR6	2 GB DDR3	8x more on A16
Bandwidth	200 GB/s	29 GB/s	6.9x higher on A16
Bus width	128-bit	128-bit	Identical
Compute · dense
FP16 / BF16	17.9 TFLOPS	Not supported	A16 only
INT8	35.9 TOPS	Not supported	A16 only
FP32	4.5 TFLOPS	0.9 TFLOPS	5.2x higher on A16
Platform
Interconnect	PCIe only	PCIe only
Released	Q2 2021	Q3 2014	7 years newer on A16
Precision
Supported formats	FP16BF16TF32FP32INT4INT8	FP32