The H20 has 8x the memory and 7.9x the bandwidth.
At a glance
Memory
8x more on H20
- H20
- 96 GB
- RTX 4070
- 12 GB
Memory bandwidth
7.9x higher on H20
- H20
- 4,000 GB/s
- RTX 4070
- 504 GB/s
Cheapest on-demand
- H20
- --
- RTX 4070
- $0.11 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | H20 | RTX 4070 | Difference |
|---|---|---|---|
| On-demand | No on-demand listings | $0.15 /GPU/hr from $0.11 | |
| Reserved | No reserved listings | -- /GPU/hr from $0.09 (48 mo) | |
| Spot | No spot listings | -- /GPU/hr from $0.06 |
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. No median for reserved and spot on the RTX 4070: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.
Price history
H20 vs RTX 4070 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | H20 | RTX 4070 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 96 GB HBM3 | 12 GB GDDR6X | 8x more on H20 |
| Bandwidth | 4,000 GB/s | 504 GB/s | 7.9x higher on H20 |
| Bus width | 192-bit | ||
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 400 W | 200 W | 2x higher on H20 |
| Released | Q1 2024 | Q2 2023 | 9 months newer on H20 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Source: RTX 4070 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 | H20 | RTX 4070 |
|---|---|---|
Vast.ai
USA
|
-- | $0.11 /GPU/hr On-demand |
Theta EdgeCloud
Distributed
|
-- | $0.16 /GPU/hr On-demand |
Salad
Distributed
|
-- | $0.15 /GPU/hr On-demand |
Similar GPUs
Other comparisons in the same class.
-
Nvidia H100
80 GB HBM3 · 16% less bandwidth than the H20
From $1.73 /GPU/hr Compare -
Nvidia A100
80 GB HBM2e · 52% less bandwidth than the H20
From $0.40 /GPU/hr Compare
-
Nvidia L40S
48 GB GDDR6 · 78% less bandwidth than the H20
From $0.55 /GPU/hr Compare
-
Nvidia RTX 5070
12 GB GDDR7 · 33% more bandwidth than the RTX 4070
From $0.16 /GPU/hr Compare
-
Nvidia RTX 4060 Ti
16 GB GDDR6 · 43% less bandwidth than the RTX 4070
From $0.09 /GPU/hr Compare
Our data for Nvidia H20 was last updated on Sept. 14, 2026, and for Nvidia RTX 4070 on Sept. 14, 2026.