Two Nvidia consumer GPUs, one Ampere and one Ada Lovelace: 24 GB GDDR6X against 12 GB GDDR6X and 2x the memory bandwidth on the RTX 3090 Ti.
At a glance
Memory
- RTX 3090 Ti
- 24 GB
- RTX 4070
- 12 GB
2x more on RTX 3090 Ti
Memory bandwidth
- RTX 3090 Ti
- 1,008 GB/s
- RTX 4070
- 504 GB/s
2x higher on RTX 3090 Ti
Cheapest on-demand
- RTX 3090 Ti
- $0.19 /GPU/hr
- RTX 4070
- $0.08 /GPU/hr
2.3x more expensive on RTX 3090 Ti
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | RTX 3090 Ti | RTX 4070 | Difference |
|---|---|---|---|
| On-demand | $0.27 /GPU/hr from $0.19 | $0.15 /GPU/hr from $0.08 | 44% cheaper on RTX 4070 |
| Reserved | No reserved listings | -- /GPU/hr from $0.09 (1 mo) | |
| Spot | -- /GPU/hr from $0.10 | -- /GPU/hr from $0.02 |
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 spot on the RTX 3090 Ti and 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
RTX 3090 Ti vs RTX 4070 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX 3090 Ti | RTX 4070 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR6X | 12 GB GDDR6X | 2x more on RTX 3090 Ti |
| Bandwidth | 1,008 GB/s | 504 GB/s | 2x higher on RTX 3090 Ti |
| Bus width | 384-bit | 192-bit | 2x wider on RTX 3090 Ti |
| Compute · dense | |||
| FP8 | Not supported | 116.6 TFLOPS | RTX 4070 only |
| FP16 / BF16 | 80 TFLOPS | 58.3 TFLOPS | 1.4x higher on RTX 3090 Ti |
| INT8 | 320 TOPS | 233.2 TOPS | 1.4x higher on RTX 3090 Ti |
| FP32 | 40 TFLOPS | 29.1 TFLOPS | 1.4x higher on RTX 3090 Ti |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 450 W | 200 W | 2.2x higher on RTX 3090 Ti |
| Released | Q1 2022 | Q2 2023 | 12 months newer on RTX 4070 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 3090 Ti datasheet and RTX 4070 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | RTX 3090 Ti /GPU/hr | RTX 4070 /GPU/hr |
|---|---|---|
Salad
|
On-Demand $0.19 | On-Demand $0.15 |
Vast.ai
|
On-Demand $0.20 | On-Demand $0.08 |
Runpod
|
On-Demand $0.27 | -- |
Theta EdgeCloud
|
-- | On-Demand $0.16 |
Similar GPUs
Other comparisons in the same class.
-
Nvidia RTX 5090
32 GB GDDR7 · 78% more bandwidth than the RTX 3090 Ti
From $0.35 /GPU/hr Compare -
Nvidia RTX 4090
24 GB GDDR6X · released Q4 2022
From $0.23 /GPU/hr Compare
-
Nvidia RTX 3090
24 GB GDDR6X · NVLink 112 GB/s
From $0.10 /GPU/hr Compare
-
Nvidia RTX 5070
12 GB GDDR7 · 33% more bandwidth than the RTX 4070
From $0.10 /GPU/hr Compare
-
Nvidia RTX 4060 Ti
16 GB GDDR6 · 43% less bandwidth than the RTX 4070
From $0.07 /GPU/hr Compare
Our data for Nvidia RTX 3090 Ti was last updated on Sept. 14, 2026, and for Nvidia RTX 4070 on Sept. 14, 2026.