Two Nvidia consumer GPUs on the Ada Lovelace architecture: 12 GB GDDR6X against 16 GB GDDR6X and 42% more memory bandwidth on the RTX 4080.
At a glance
Memory
- RTX 4070
- 12 GB
- RTX 4080
- 16 GB
1.3x more on RTX 4080
Memory bandwidth
- RTX 4070
- 504 GB/s
- RTX 4080
- 717 GB/s
1.4x higher on RTX 4080
Cheapest on-demand
- RTX 4070
- $0.15 /GPU/hr
- RTX 4080
- $0.25 /GPU/hr
39% cheaper on RTX 4070
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | RTX 4070 | RTX 4080 | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $0.15 | $0.27 /GPU/hr from $0.25 | |
| Spot | -- /GPU/hr from $0.07 | -- /GPU/hr from $0.11 |
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 4070 and spot on the RTX 4080: 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 4070 vs RTX 4080 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX 4070 | RTX 4080 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 12 GB GDDR6X | 16 GB GDDR6X | 1.3x more on RTX 4080 |
| Bandwidth | 504 GB/s | 717 GB/s | 1.4x higher on RTX 4080 |
| Bus width | 192-bit | 256-bit | 1.3x wider on RTX 4080 |
| Compute · dense | |||
| FP8 | 116.6 TFLOPS | 194.9 TFLOPS | 1.7x higher on RTX 4080 |
| FP16 / BF16 | 58.3 TFLOPS | 97.5 TFLOPS | 1.7x higher on RTX 4080 |
| INT8 | 233.2 TOPS | 389.9 TOPS | 1.7x higher on RTX 4080 |
| FP32 | 29.1 TFLOPS | 48.7 TFLOPS | 1.7x higher on RTX 4080 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 200 W | 320 W | 1.6x higher on RTX 4080 |
| Released | Q2 2023 | Q4 2022 | |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT4INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 4070 datasheet and RTX 4080 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | RTX 4070 /GPU/hr | RTX 4080 /GPU/hr |
|---|---|---|
Salad
|
On-Demand $0.15 | On-Demand $0.28 |
Theta EdgeCloud
|
On-Demand $0.17 | On-Demand $0.26 |
GPUhub
|
-- | On-Demand $0.25 |
SwissGPU
|
-- | On-Demand $0.25 |
Runpod
|
-- | On-Demand $0.27 |
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia RTX 4070 was last updated on Sept. 7, 2026, and for Nvidia RTX 4080 on Sept. 7, 2026.