Nvidia K80 vs Nvidia V100

The V100 is newer, with 2.7x the memory and 3.8x the bandwidth, and is cheaper right now.

At a glance

Memory

2.7x more on V100

K80: 12 GB

V100: 32 GB

Memory bandwidth

3.8x higher on V100

K80: 240 GB/s

V100: 900 GB/s

Cheapest on-demand

91% cheaper on V100

K80: $0.90 /GPU/hr

V100: $0.08 /GPU/hr

Price comparison

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

Billing	K80	V100
On-demand	-- /GPU/hr from $0.90	$0.99 /GPU/hr from $0.08
Reserved	-- /GPU/hr from $0.04 (24 mo)	$1.51 /GPU/hr from $0.09 (1 mo)
Spot	No spot listings	$0.43 /GPU/hr from $0.07

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: 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 V100 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	K80	V100	Difference
Memory
Capacity	12 GB GDDR5	32 GB HBM2	2.7x more on V100
Bandwidth	240 GB/s	900 GB/s	3.8x higher on V100
Bus width	384-bit	4,096-bit	11x wider on V100
Compute · dense
FP16 / BF16	Not supported	125 TFLOPS	V100 only
FP32	4.4 TFLOPS	15.7 TFLOPS	3.6x higher on V100
FP64	1.5 TFLOPS	7.8 TFLOPS	5.3x higher on V100
Platform
Interconnect	PCIe only	NVLink 300 GB/s	NVLink on V100 only
Board power	150 W	300 W	2x higher on V100
Released	Q4 2014	Q2 2017	3 years newer on V100
Precision
Supported formats	FP32FP64	FP16FP32FP64INT8

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: K80 datasheet and V100 datasheet.

Where to rent them

Providers that rent these GPUs, with each one's cheapest rate. No provider we track offers both right now.

Provider	K80	V100
AWS USA	$0.90 /GPU/hr On-demand	--
Database Mart USA	$0.0447 /GPU/hr Reserved	--
GPU.ai UAE	--	$0.08 /GPU/hr On-demand
Vast.ai USA	--	$0.09 /GPU/hr On-demand
HyperAI Hong Kong	--	$0.14 /GPU/hr On-demand
Runcrate USA	--	$2.57 /GPU/hr On-demand NVL
Sesterce France	--	$2.57 /GPU/hr On-demand
Geodd USA	--	$0.16 /GPU/hr On-demand
TensorDock Distributed	--	$0.28 /GPU/hr On-demand SXM
Cyfuture AI India	--	$0.55 /GPU/hr On-demand