Two Nvidia consumer GPUs, one Ampere and one Ada Lovelace: 8 GB GDDR6 against 24 GB GDDR6X and 2.3x the memory bandwidth on the RTX 4090.
At a glance
Updated 5 minutes ago- Memory
- 8 GB
- GDDR6
- Memory bandwidth
- 448 GB/s
- From
- $0.08 /GPU/hr
- 4 providers
- Memory
- 24 GB
- GDDR6X
- Memory bandwidth
- 1.01 TB/s
- From
- $0.23 /GPU/hr
- 18 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | RTX 3070 | RTX 4090 | Difference |
|---|---|---|---|
| On-demand | $0.08 | $0.23 | 3x more expensive on RTX 4090 |
| Spot | $0.04 | $0.15 | 3.7x more expensive on RTX 4090 |
| Reserved | $0.11 | $0.27 | 2.4x more expensive on RTX 4090 |
| Median | $0.12 | $0.41 | 3.5x more expensive on RTX 4090 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
RTX 3070 vs RTX 4090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX 3070 | RTX 4090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 8 GB GDDR6 | 24 GB GDDR6X | 3x more on RTX 4090 |
| Bandwidth | 448 GB/s | 1,010 GB/s | 2.3x 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 | 40.6 TFLOPS | 165.2 TFLOPS | 4.1x higher on RTX 4090 |
| INT8 | 162.6 TOPS | 660.6 TOPS | 4.1x higher on RTX 4090 |
| FP32 | 20.3 TFLOPS | 82.6 TFLOPS | 4.1x higher on RTX 4090 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 220 W | 450 W | 2x higher on RTX 4090 |
| Released | Q4 2020 | Q4 2022 | 2 years newer on RTX 4090 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 3070 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 /GPU/hr | RTX 4090 /GPU/hr |
|---|---|---|
Vast.ai
|
On-Demand $0.08 | On-Demand $0.32 |
Theta EdgeCloud
|
On-Demand $0.10 | On-Demand $0.23 |
Salad
|
On-Demand $0.10 | On-Demand $0.30 |
Runpod
|
On-Demand $0.13 | On-Demand $0.34 |
Lium
|
-- | On-Demand $0.30 |
Novita
|
-- | On-Demand $0.33 |
GPU.ai
|
-- | On-Demand $0.34 |
Packet·ai
|
-- | On-Demand $0.39 |
4 providers list the RTX 3070 and 18 the RTX 4090. Every listing is on the RTX 3070 page and the RTX 4090 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia RTX 3070 was last updated on Sept. 7, 2026, and for Nvidia RTX 4090 on Sept. 7, 2026.