A data center GPU against a consumer card, one Hopper and one Turing: 80 GB HBM2e against 8 GB GDDR6, 4.5x the memory bandwidth on the H800, and NVLink 400 GB/s on the H800 where the RTX 2070 is PCIe only.

At a glance

Updated 21 minutes ago
Memory
80 GB
HBM2e
Memory bandwidth
2.00 TB/s
From
--
Memory
8 GB
GDDR6
Memory bandwidth
448 GB/s
From
$0.05 /GPU/hr
2 providers

Price comparison

Cheapest listed price per GPU per hour by billing type, and the median across providers.

Billing H800 RTX 2070 Difference
On-demand -- $0.05
Spot No spot listings $0.02
Median -- $0.06

Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.

Price history

H800 vs RTX 2070 price history

Weekly median on-demand price per GPU per hour

Last 12 months
Aggregating historical prices...

Specs comparison

Spec H800 RTX 2070 Difference
Memory
Capacity 80 GB HBM2e 8 GB GDDR6 10x more on H800
Bandwidth 2,000 GB/s 448 GB/s 4.5x higher on H800
Bus width 5,120-bit 256-bit 20x wider on H800
Compute · dense
FP8 1,513 TFLOPS Not supported H800 only
FP16 / BF16 756.5 TFLOPS 29.9 TFLOPS 25x higher on H800
INT8 1,513 TOPS 119.4 TOPS 13x higher on H800
FP32 51 TFLOPS 7.5 TFLOPS 6.8x higher on H800
Platform
Interconnect NVLink 400 GB/s PCIe only NVLink on H800 only
Board power 350 W 175 W 2x higher on H800
Released Q1 2023 Q4 2018 4 years newer on H800
Precision
Supported formats FP8FP16BF16TF32FP32FP64INT8 FP16FP32INT4INT8

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

Source: RTX 2070 datasheet.

Where to rent them

Providers listing these GPUs, those with both first, so you can switch without moving clouds.

Provider H800 /GPU/hr RTX 2070 /GPU/hr
Vast.ai logo Vast.ai -- On-Demand $0.05
Salad logo Salad -- On-Demand $0.06

Similar GPUs

Other comparisons in the same class.

Our data for Nvidia H800 was last updated on Sept. 7, 2026, and for Nvidia RTX 2070 on Sept. 7, 2026.