Home
Compare GPUs
H800 vs K80

Nvidia H800 vs Nvidia K80

Two Nvidia data center GPUs, one Hopper and one Kepler: 80 GB HBM2e against 12 GB GDDR5, 8.3x the memory bandwidth on the H800, and NVLink 400 GB/s on the H800 where the K80 is PCIe only.

At a glance

Memory

H800: 80 GB
K80: 12 GB

6.7x more on H800

Memory bandwidth

H800: 2,000 GB/s
K80: 240 GB/s

8.3x higher on H800

Cheapest on-demand

H800: --
K80: $0.90 /GPU/hr

Price comparison

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

Billing	H800	K80	Difference
On-demand	No on-demand listings	-- /GPU/hr from $0.90
Reserved	No reserved listings	-- /GPU/hr from $0.04 (24 mo)

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

H800 vs K80 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	H800	K80	Difference
Memory
Capacity	80 GB HBM2e	12 GB GDDR5	6.7x more on H800
Bandwidth	2,000 GB/s	240 GB/s	8.3x higher on H800
Bus width	5,120-bit	384-bit	13x wider on H800
Compute · dense
FP8	1,513 TFLOPS	Not supported	H800 only
FP16 / BF16	756.5 TFLOPS	Not supported	H800 only
INT8	1,513 TOPS	Not supported	H800 only
FP32	51 TFLOPS	4.4 TFLOPS	12x higher on H800
FP64		1.5 TFLOPS
Platform
Interconnect	NVLink 400 GB/s	PCIe only	NVLink on H800 only
Board power	350 W	150 W	2.3x higher on H800
Released	Q1 2023	Q4 2014	8 years newer on H800
Precision
Supported formats	FP8FP16BF16TF32FP32FP64INT8	FP32FP64