Nvidia K80 vs Nvidia V100S

The V100S is newer, with 2.7x the memory and 4.7x the bandwidth.

At a glance

Memory

2.7x more on V100S

K80: 12 GB

V100S: 32 GB

Memory bandwidth

4.7x higher on V100S

K80: 240 GB/s

V100S: 1,134 GB/s

Cheapest on-demand

Within 5%

K80: $0.90 /GPU/hr

V100S: $0.88 /GPU/hr

Price comparison

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

Billing	K80	V100S	Difference
On-demand	-- /GPU/hr from $0.90	-- /GPU/hr from $0.88
Reserved	-- /GPU/hr from $0.04 (24 mo)	No reserved 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 reserved on the K80 and on-demand on the V100S: 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

K80 vs V100S price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	K80	V100S	Difference
Memory
Capacity	12 GB GDDR5	32 GB HBM2	2.7x more on V100S
Bandwidth	240 GB/s	1,134 GB/s	4.7x higher on V100S
Bus width	384-bit	4,096-bit	11x wider on V100S
Compute · dense
FP16 / BF16	Not supported	130 TFLOPS	V100S only
FP32	4.4 TFLOPS	16.4 TFLOPS	3.8x higher on V100S
FP64	1.5 TFLOPS	8.2 TFLOPS	5.6x higher on V100S
Platform
Interconnect	PCIe only	NVLink 300 GB/s	NVLink on V100S only
Board power	150 W	250 W	67% higher on V100S
Released	Q4 2014	Q4 2019	5 years newer on V100S
Precision
Supported formats	FP32FP64	FP16FP32FP64INT8