Nvidia K80 vs Nvidia P4

The K80 has 50% more memory and 25% more bandwidth. The P4 is newer and cheaper right now.

At a glance

Memory

50% more on K80

K80: 12 GB

P4: 8 GB

Memory bandwidth

25% higher on K80

K80: 240 GB/s

P4: 192 GB/s

Cheapest on-demand

27% cheaper on P4

K80: $0.90 /GPU/hr

P4: $0.65 /GPU/hr

Price comparison

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

Billing	K80	P4
On-demand	-- /GPU/hr from $0.90	-- /GPU/hr from $0.65
Reserved	-- /GPU/hr from $0.04 (24 mo)	-- /GPU/hr from $0.34 (36 mo)
Spot	No spot listings	-- /GPU/hr from $0.11

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, reserved and spot on the P4: 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 P4 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	K80	P4	Difference
Memory
Capacity	12 GB GDDR5	8 GB GDDR5	50% more on K80
Bandwidth	240 GB/s	192 GB/s	25% higher on K80
Bus width	384-bit	256-bit	50% wider on K80
Compute · dense
INT8	Not supported	22 TOPS	P4 only
FP32	4.4 TFLOPS	5.5 TFLOPS	26% higher on P4
FP64	1.5 TFLOPS	Not supported	K80 only
Platform
Interconnect	PCIe only	PCIe only
Board power	150 W	75 W	2x higher on K80
Released	Q4 2014	Q3 2016	2 years newer on P4
Precision
Supported formats	FP32FP64	FP16FP32INT8