Two Nvidia consumer GPUs, one Ampere and one Ada Lovelace: 8 GB GDDR6X against 24 GB GDDR6X and 66% more memory bandwidth on the RTX 4090.
At a glance
Memory
- RTX 3070 Ti
- 8 GB
- RTX 4090
- 24 GB
3x more on RTX 4090
Memory bandwidth
- RTX 3070 Ti
- 608 GB/s
- RTX 4090
- 1,010 GB/s
1.7x higher on RTX 4090
Cheapest on-demand
- RTX 3070 Ti
- $0.10 /GPU/hr
- RTX 4090
- $0.23 /GPU/hr
2.3x more expensive on RTX 4090
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | RTX 3070 Ti | RTX 4090 | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $0.10 | $0.44 /GPU/hr from $0.23 | |
| Reserved | No reserved listings | $0.41 /GPU/hr from $0.27 (12 mo) | |
| Spot | -- /GPU/hr from $0.06 | $0.17 /GPU/hr from $0.16 |
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 on-demand and spot on the RTX 3070 Ti: 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 3070 Ti vs RTX 4090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX 3070 Ti | RTX 4090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 8 GB GDDR6X | 24 GB GDDR6X | 3x more on RTX 4090 |
| Bandwidth | 608 GB/s | 1,010 GB/s | 1.7x higher on RTX 4090 |
| Bus width | 256-bit | 384-bit | 1.5x wider on RTX 4090 |
| Compute · dense | |||
| FP8 | Not supported | 330.3 TFLOPS | RTX 4090 only |
| FP16 / BF16 | 43.5 TFLOPS | 165.2 TFLOPS | 3.8x higher on RTX 4090 |
| INT8 | 174 TOPS | 660.6 TOPS | 3.8x higher on RTX 4090 |
| FP32 | 21.8 TFLOPS | 82.6 TFLOPS | 3.8x higher on RTX 4090 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 290 W | 450 W | 1.6x higher on RTX 4090 |
| Released | Q2 2021 | Q4 2022 | 16 months newer on RTX 4090 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 3070 Ti datasheet and RTX 4090 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | RTX 3070 Ti /GPU/hr | RTX 4090 /GPU/hr |
|---|---|---|
Salad
|
On-Demand $0.10 | On-Demand $0.33 |
Vast.ai
|
On-Demand $0.12 | On-Demand $0.29 |
Theta EdgeCloud
|
-- | On-Demand $0.23 |
Lium
|
-- | On-Demand $0.30 |
GPU.ai
|
-- | On-Demand $0.32 |
Novita
|
-- | On-Demand $0.33 |
Runpod
|
-- | On-Demand $0.34 |
Packet·ai
|
-- | On-Demand $0.39 |
2 providers list the RTX 3070 Ti and 20 the RTX 4090. Every listing is on the RTX 3070 Ti page and the RTX 4090 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia RTX 3080
10 GB GDDR6X · 25% more bandwidth than the RTX 3070 Ti
From $0.09 /GPU/hr Compare -
Nvidia RTX 3070
8 GB GDDR6 · 26% less bandwidth than the RTX 3070 Ti
From $0.07 /GPU/hr Compare
-
Nvidia RTX 4070
12 GB GDDR6X · 17% less bandwidth than the RTX 3070 Ti
From $0.08 /GPU/hr Compare
-
Nvidia RTX 5090
32 GB GDDR7 · 77% more bandwidth than the RTX 4090
From $0.35 /GPU/hr Compare
-
Nvidia L40S
48 GB GDDR6 · 14% less bandwidth than the RTX 4090
From $0.53 /GPU/hr Compare
Our data for Nvidia RTX 3070 Ti was last updated on Sept. 14, 2026, and for Nvidia RTX 4090 on Sept. 14, 2026.