The H20 is newer, with 48x the memory and 286x the bandwidth.
At a glance
Memory
48x more on H20
- GT 730
- 2 GB
- H20
- 96 GB
Memory bandwidth
286x higher on H20
- GT 730
- 14 GB/s
- H20
- 4,000 GB/s
Cheapest on-demand
- GT 730
- --
- H20
- --
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
Price history
GT 730 vs H20 price history
Weekly median on-demand price per GPU per hour
Aggregating historical prices...
Specs comparison
| Spec | GT 730 | H20 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 2 GB DDR3 | 96 GB HBM3 | 48x more on H20 |
| Bandwidth | 14 GB/s | 4,000 GB/s | 286x higher on H20 |
| Bus width | 64-bit | ||
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 23 W | 400 W | 17x higher on H20 |
| Released | Q2 2014 | Q1 2024 | 10 years newer on H20 |
| Precision | |||
| Supported formats | FP32 | FP8FP16BF16TF32FP32FP64INT8 | |
Similar GPUs
Other comparisons in the same class.
-
Nvidia GTX 1050 Ti
4 GB GDDR5 · 8x the bandwidth of the GT 730
From $0.02 /GPU/hr Compare -
Nvidia H100
80 GB HBM3 · 16% less bandwidth than the H20
From $1.30 /GPU/hr Compare
-
Nvidia A100
80 GB HBM2e · 52% less bandwidth than the H20
From $0.37 /GPU/hr Compare
Our data for Nvidia GT 730 was last updated on Sept. 14, 2026, and for Nvidia H20 on Sept. 14, 2026.