Two Nvidia data center GPUs, one Hopper and one Turing: 96 GB HBM3 against 16 GB GDDR6 and 13x the memory bandwidth on the H20.
At a glance
Updated 3 minutes ago- Memory
- 96 GB
- HBM3
- Memory bandwidth
- 4.00 TB/s
- From
- --
- Memory
- 16 GB
- GDDR6
- Memory bandwidth
- 300 GB/s
- From
- $0.15 /GPU/hr
- 11 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | H20 | T4 | Difference |
|---|---|---|---|
| On-demand | -- | $0.15 | |
| Spot | No spot listings | $0.06 | |
| Reserved | No reserved listings | $0.20 | |
| Median | -- | $0.64 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
H20 vs T4 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | H20 | T4 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 96 GB HBM3 | 16 GB GDDR6 | 6x more on H20 |
| Bandwidth | 4,000 GB/s | 300 GB/s | 13x higher on H20 |
| Bus width | 256-bit | ||
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 400 W | 70 W | 5.7x higher on H20 |
| Released | Q1 2024 | Q3 2018 | 5 years newer on H20 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP16FP32INT4INT8 | |
Source: T4 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | H20 /GPU/hr | T4 /GPU/hr |
|---|---|---|
Vast.ai
|
-- | On-Demand $0.15 |
Zenlayer
|
-- | On-Demand $0.56 |
Theta EdgeCloud
|
-- | On-Demand $0.20 |
Hugging Face
|
-- | On-Demand $0.40 |
Google Cloud
|
-- | On-Demand $0.42 |
AWS
|
-- | On-Demand $0.53 |
Azure
|
-- | On-Demand $0.53 |
Cerebrium
|
-- | On-Demand $0.59 |
0 providers list the H20 and 11 the T4. Every listing is on the H20 page and the T4 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia H20 was last updated on Sept. 7, 2026, and for Nvidia T4 on Sept. 7, 2026.