The RTX 4000 SFF Ada is newer, with 3.3x the memory and 46% more bandwidth. The GTX 1660 is cheaper right now.
At a glance
Memory
3.3x more on RTX 4000 SFF Ada
- GTX 1660
- 6 GB
- RTX 4000 SFF Ada
- 20 GB
Memory bandwidth
46% higher on RTX 4000 SFF Ada
- GTX 1660
- 192 GB/s
- RTX 4000 SFF Ada
- 280 GB/s
Cheapest on-demand
90% cheaper on GTX 1660
- GTX 1660
- $0.04 /GPU/hr
- RTX 4000 SFF Ada
- $0.42 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | GTX 1660 | RTX 4000 SFF Ada | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $0.04 | -- /GPU/hr from $0.42 | |
| Reserved | -- /GPU/hr from $0.19 (24 mo) | No reserved listings | |
| 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, reserved and spot on the GTX 1660 and on-demand on the RTX 4000 SFF Ada: 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 vs RTX 4000 SFF Ada price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | GTX 1660 | RTX 4000 SFF Ada | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 6 GB GDDR5 | 20 GB GDDR6 | 3.3x more on RTX 4000 SFF Ada |
| Bandwidth | 192 GB/s | 280 GB/s | 46% higher on RTX 4000 SFF Ada |
| Bus width | 192-bit | 160-bit | 20% wider on GTX 1660 |
| Compute · dense | |||
| FP8 | Not supported | 153.4 TFLOPS | RTX 4000 SFF Ada only |
| FP16 / BF16 | 10.1 TFLOPS | 76.7 TFLOPS | 7.6x higher on RTX 4000 SFF Ada |
| FP32 | 5.0 TFLOPS | 19.2 TFLOPS | 3.8x higher on RTX 4000 SFF Ada |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 120 W | 70 W | 71% higher on GTX 1660 |
| Released | Q1 2019 | Q2 2023 | 4 years newer on RTX 4000 SFF Ada |
| Precision | |||
| Supported formats | FP16FP32 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: GTX 1660 datasheet and RTX 4000 SFF Ada 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 | RTX 4000 SFF Ada |
|---|---|---|
Salad
Distributed
|
$0.0400 /GPU/hr On-demand | -- |
Vast.ai
USA
|
$0.07 /GPU/hr On-demand | -- |
Database Mart
USA
|
$0.19 /GPU/hr Reserved | -- |
Hetzner
Germany
|
-- | $0.42 /GPU/hr On-demand |
Koyeb
France
|
-- | $0.50 /GPU/hr On-demand |
Runpod
USA
|
-- | $0.18 /GPU/hr On-demand |
Similar GPUs
Other comparisons in the same class.
-
Nvidia RTX 3060
12 GB GDDR6 · 88% more bandwidth than the GTX 1660
From $0.05 /GPU/hr Compare -
Nvidia RTX 2060
6 GB GDDR6 · 75% more bandwidth than the GTX 1660
From $0.05 /GPU/hr Compare
-
Nvidia GTX 1660 Super
6 GB GDDR6 · 75% more bandwidth than the GTX 1660
From $0.04 /GPU/hr Compare
-
Nvidia L4
24 GB GDDR6 · data center card
From $0.27 /GPU/hr Compare
Our data for Nvidia GTX 1660 was last updated on Sept. 14, 2026, and for Nvidia RTX 4000 SFF Ada on Sept. 14, 2026.