Nvidia RTX A6000 vs Nvidia H800

The H800 is newer, with 67% more memory and 2.6x the bandwidth.

At a glance

Memory

67% more on H800

RTX A6000: 48 GB

H800: 80 GB

Memory bandwidth

2.6x higher on H800

RTX A6000: 768 GB/s

H800: 2,000 GB/s

Cheapest on-demand

RTX A6000: $0.35 /GPU/hr

H800: --

Price comparison

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

Billing	RTX A6000	H800
On-demand	$0.56 /GPU/hr from $0.35	No on-demand listings
Reserved	$0.48 /GPU/hr from $0.26 (6 mo)	No reserved listings
Spot	$0.33 /GPU/hr from $0.13	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. Verify before provisioning. More on how we price.

Price history

RTX A6000 vs H800 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	RTX A6000	H800	Difference
Memory
Capacity	48 GB GDDR6	80 GB HBM2e	67% more on H800
Bandwidth	768 GB/s	2,000 GB/s	2.6x higher on H800
Bus width	384-bit	5,120-bit	13x wider on H800
Compute · dense
FP8	Not supported	1,513 TFLOPS	H800 only
FP16 / BF16	154.8 TFLOPS	756.5 TFLOPS	4.9x higher on H800
INT8	309.7 TOPS	1,513 TOPS	4.9x higher on H800
FP32	38.7 TFLOPS	51 TFLOPS	32% higher on H800
Platform
Interconnect	NVLink 112 GB/s	NVLink 400 GB/s	3.6x higher on H800
Board power	300 W	350 W	17% higher on H800
Released	Q4 2020	Q1 2023	2 years newer on H800
Precision
Supported formats	FP16BF16TF32FP32INT4INT8	FP8FP16BF16TF32FP32FP64INT8

Compute: Vendor peak figures, dense and per GPU. Not measured throughput.

Source: RTX A6000 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	RTX A6000	H800
Thunder Compute USA	$0.35 /GPU/hr On-demand	--
Vast.ai USA	$0.39 /GPU/hr On-demand	--
GPU.ai UAE	$0.40 /GPU/hr On-demand	--
Spheron Singapore	$0.53 /GPU/hr On-demand PCIe	--
Runpod USA	$0.53 /GPU/hr On-demand	--
Massed Compute USA	$0.55 /GPU/hr On-demand	--
Oblivus USA	$0.55 /GPU/hr On-demand PCIe	--
Sesterce France	$0.55 /GPU/hr On-demand	--