A data center GPU against a workstation card, one Hopper and one Ada Lovelace: 96 GB HBM3 against 16 GB GDDR6 and 18x the memory bandwidth on the H20.

At a glance

Memory

H20
96 GB
RTX 2000 Ada
16 GB

6x more on H20

Memory bandwidth

H20
4,000 GB/s
RTX 2000 Ada
224 GB/s

18x higher on H20

Cheapest on-demand

H20
--
RTX 2000 Ada
$0.13 /GPU/hr

Price comparison

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

Billing H20 RTX 2000 Ada Difference
On-demand No on-demand listings $0.24 /GPU/hr from $0.13
Reserved No reserved listings On request

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

H20 vs RTX 2000 Ada price history

Weekly median on-demand price per GPU per hour

Last 9 weeks
Aggregating historical prices...

Specs comparison

Spec H20 RTX 2000 Ada Difference
Memory
Capacity 96 GB HBM3 16 GB GDDR6 6x more on H20
Bandwidth 4,000 GB/s 224 GB/s 18x higher on H20
Bus width 128-bit
Platform
Interconnect PCIe only PCIe only
Board power 400 W 70 W 5.7x higher on H20
Released Q1 2024 Q2 2024
Precision
Supported formats FP8FP16BF16TF32FP32FP64INT8 FP8FP16BF16TF32FP32INT4INT8

Where to rent them

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

Provider H20 /GPU/hr RTX 2000 Ada /GPU/hr
Theta EdgeCloud logo Theta EdgeCloud -- On-Demand $0.13
GPU.ai logo GPU.ai -- On-Demand $0.24
Runpod logo Runpod -- On-Demand $0.24

Similar GPUs

Other comparisons in the same class.

Our data for Nvidia H20 was last updated on Sept. 14, 2026, and for Nvidia RTX 2000 Ada on Sept. 14, 2026.