Two Nvidia consumer GPUs, one Turing and one Ada Lovelace: 6 GB GDDR5 against 16 GB GDDR6X and 3.7x the memory bandwidth on the RTX 4080.
At a glance
Updated 7 minutes ago- Memory
- 6 GB
- GDDR5
- Memory bandwidth
- 192 GB/s
- From
- $0.04 /GPU/hr
- 3 providers
- Memory
- 16 GB
- GDDR6X
- Memory bandwidth
- 717 GB/s
- From
- $0.14 /GPU/hr
- 6 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | GTX 1660 | RTX 4080 | Difference |
|---|---|---|---|
| On-demand | $0.04 | $0.14 | 3.4x more expensive on RTX 4080 |
| Spot | $0.02 | $0.11 | 5.5x more expensive on RTX 4080 |
| Reserved | $0.19 | No reserved listings | |
| Median | $0.36 | $0.25 | 30% cheaper on RTX 4080 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
GTX 1660 vs RTX 4080 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | GTX 1660 | RTX 4080 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 6 GB GDDR5 | 16 GB GDDR6X | 2.7x more on RTX 4080 |
| Bandwidth | 192 GB/s | 717 GB/s | 3.7x higher on RTX 4080 |
| Bus width | 192-bit | 256-bit | 1.3x wider on RTX 4080 |
| Compute · dense | |||
| FP8 | Not supported | 194.9 TFLOPS | RTX 4080 only |
| FP16 / BF16 | 10.1 TFLOPS | 97.5 TFLOPS | 9.7x higher on RTX 4080 |
| INT8 | Not supported | 389.9 TOPS | RTX 4080 only |
| FP32 | 5.0 TFLOPS | 48.7 TFLOPS | 9.7x higher on RTX 4080 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 120 W | 320 W | 2.7x higher on RTX 4080 |
| Released | Q1 2019 | Q4 2022 | 4 years newer on RTX 4080 |
| Precision | |||
| Supported formats | FP16FP32 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: GTX 1660 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 | GTX 1660 /GPU/hr | RTX 4080 /GPU/hr |
|---|---|---|
Salad
|
On-Demand $0.0400 | On-Demand $0.28 |
Vast.ai
|
On-Demand $0.68 | On-Demand $0.14 |
Database Mart
|
Reserved (24mo) $0.19 | -- |
GPUhub
|
-- | On-Demand $0.25 |
Theta EdgeCloud
|
-- | On-Demand $0.26 |
SwissGPU
|
-- | On-Demand $0.25 |
Runpod
|
-- | On-Demand $0.27 |
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia GTX 1660 was last updated on Sept. 7, 2026, and for Nvidia RTX 4080 on Sept. 7, 2026.