The RTX PRO 4500 is newer, with 5.3x the memory and 2.7x the bandwidth. The GTX 1660 Super is cheaper right now.
At a glance
Memory
5.3x more on RTX PRO 4500
- GTX 1660 Super
- 6 GB
- RTX PRO 4500
- 32 GB
Memory bandwidth
2.7x higher on RTX PRO 4500
- GTX 1660 Super
- 336 GB/s
- RTX PRO 4500
- 896 GB/s
Cheapest on-demand
94% cheaper on GTX 1660 Super
- GTX 1660 Super
- $0.04 /GPU/hr
- RTX PRO 4500
- $0.72 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | GTX 1660 Super | RTX PRO 4500 | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $0.04 | $0.92 /GPU/hr from $0.72 | |
| Reserved | No reserved listings | On request | |
| Spot | -- /GPU/hr from $0.02 | No spot listings |
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 GTX 1660 Super: 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
GTX 1660 Super vs RTX PRO 4500 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | GTX 1660 Super | RTX PRO 4500 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 6 GB GDDR6 | 32 GB GDDR7 | 5.3x more on RTX PRO 4500 |
| Bandwidth | 336 GB/s | 896 GB/s | 2.7x higher on RTX PRO 4500 |
| Bus width | 192-bit | 256-bit | 33% wider on RTX PRO 4500 |
| Compute · dense | |||
| FP4 | Not supported | 808.5 TFLOPS | RTX PRO 4500 only |
| FP8 | Not supported | 404.3 TFLOPS | RTX PRO 4500 only |
| FP16 / BF16 | 10.1 TFLOPS | 202.1 TFLOPS | 20x higher on RTX PRO 4500 |
| INT8 | Not supported | 404.3 TOPS | RTX PRO 4500 only |
| FP32 | 5.0 TFLOPS | 51 TFLOPS | 10x higher on RTX PRO 4500 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 125 W | 200 W | 60% higher on RTX PRO 4500 |
| Released | Q4 2019 | Q1 2025 | 5 years newer on RTX PRO 4500 |
| Precision | |||
| Supported formats | FP16FP32 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: GTX 1660 Super datasheet and RTX PRO 4500 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. No provider we track offers both right now.
| Provider | GTX 1660 Super | RTX PRO 4500 |
|---|---|---|
Salad
Distributed
|
$0.0400 /GPU/hr On-demand | -- |
Theta EdgeCloud
Distributed
|
$0.07 /GPU/hr On-demand | -- |
GPU.ai
UAE
|
-- | $0.72 /GPU/hr On-demand |
Runpod
USA
|
-- | $0.72 /GPU/hr On-demand |
Massed Compute
USA
|
-- | $0.92 /GPU/hr On-demand |
EmpirioLabs AI
USA
|
-- | $1.40 /GPU/hr On-demand |
AWS
USA
|
-- | $2.52 /GPU/hr On-demand |
Similar GPUs
Other comparisons in the same class.
-
-
-
Nvidia GTX 1660
6 GB GDDR5 · 43% less bandwidth than the GTX 1660 Super
On-demand from $0.04 /GPU/hr -
Nvidia RTX PRO 6000
96 GB GDDR7 · 78% more bandwidth than the RTX PRO 4500
On-demand from $0.65 /GPU/hr
-
Nvidia RTX PRO 4000
24 GB GDDR7 · 25% less bandwidth than the RTX PRO 4500
On-demand from $0.57 /GPU/hr
Our data for Nvidia GTX 1660 Super was last updated on Sept. 14, 2026, and for Nvidia RTX PRO 4500 on Sept. 14, 2026.