Flopper.io Flopper.io

NVIDIA GeForce GTX 1660 6GB vs NVIDIA T4 16GB

The T4 delivers 6.5x the FP16 throughput of the GeForce GTX 1660 (65 vs 10 TFLOPS dense). The T4 also carries 10 GB more memory (16 GB vs 6 GB).

GeForce GTX 1660: Turing, 2019 T4: Turing, 2019
FP16 dense lead
6.5x
T4: 65 vs 10 TFLOPS
Memory
6 vs 16 GB
10 GB more for the T4
Bandwidth
192 GB/s vs 300 GB/s
T4 moves data faster
TDP
120 W vs 70 W
T4 draws 50 W less
See rental pricing from $0.05/hr Download comparison sheet

Share this page

NVIDIA GeForce GTX 1660 6GB vs NVIDIA T4 16GB

A post with this link shows the card on the Image tab as its preview.

Post on X Share on LinkedIn
 Printable version →

NVIDIA GeForce GTX 1660 6GB

Full specs →

What is the NVIDIA GeForce GTX 1660?

The GeForce GTX 1660 is a GPU from NVIDIA on the Turing architecture, an accelerator for AI training, inference and high-performance computing. It is a PCIe add-in card, so it fits standard servers and workstations. GeForce GTX 1660 full specifications →

Can I rent the GeForce GTX 1660 in the cloud?

Yes. Cloud providers tracked by Flopper rent the GeForce GTX 1660 by the hour, and the pricing page compares their current rates and the price history side by side. GeForce GTX 1660 rental prices →

How does the GeForce GTX 1660 compare with other accelerators?

This page sets the GeForce GTX 1660 against the T4. Both parts launched in the same year. Both are NVIDIA parts, and both ship as a PCIe card, so they fit the same class of system. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the GeForce GTX 1660 figures come from?

NVIDIA published the GeForce GTX 1660 figures in marketing material rather than a datasheet, and Flopper has no independent confirmation of them. How Flopper verifies specifications →

NVIDIA T4 16GB

Leads on FP16 Full specs →

What is the NVIDIA T4?

The T4 is a GPU from NVIDIA on the Turing architecture, an accelerator for AI training, inference and high-performance computing. It is a PCIe add-in card, so it fits standard servers and workstations. T4 full specifications →

Can I rent the T4 in the cloud?

Yes. Cloud providers tracked by Flopper rent the T4 by the hour, and the pricing page compares their current rates and the price history side by side. T4 rental prices →

How does the T4 compare with other accelerators?

This page sets the T4 against the GeForce GTX 1660. Both parts launched in the same year. Both are NVIDIA parts, and both ship as a PCIe card, so they fit the same class of system. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the T4 figures come from?

Every T4 figure on this page traces to NVIDIA's own datasheet or specification table. How Flopper verifies specifications →

Specifications

GeForce GTX 1660
T4
Architecture
TuringTuring
Launch Year
20192019
Form Factor
PCIePCIe
Memory
6 GB16 GB
Memory Bandwidth
192 GB/s300 GB/s
TDP
120 W70 W
Process Node
12nm12nm

Performance (TFLOPS)

GeForce GTX 1660
T4
0.2 TFLOPS No verified data available
5 TFLOPS 8.1 TFLOPS
No verified data available No verified data available
No verified data available No verified data available
10 TFLOPS 65 TFLOPS
No verified data available No verified data available
FP6
No verified data available No verified data available
No verified data available No verified data available
No verified data available130 TOPS

Figures are dense. Where a vendor publishes a figure it sits under the dense one and never decides a winner. Hover any precision for its definition, or read the GPU glossary.

FLOPS by Precision

What actually differs

Both launched in 2019, the GeForce GTX 1660 on Turing and the T4 on Turing.

The T4 carries 10 GB more memory (16 GB against 6 GB), so larger models fit on one GPU before you shard. Bandwidth is 192 GB/s against 300 GB/s, which sets the ceiling on decode speed.

Power is 120 W against 70 W, and at FP32 the T4 does more work per watt. Weight the FP8 and FP16 rows for LLM work and the FP64 row for HPC.

New to the terms? The glossary explains FP64, FP32, FP16, INT8, Sparsity and TFLOPS. For how the generations relate, see NVIDIA architectures explained.

Frequently asked questions

Is the GeForce GTX 1660 faster than the T4?

At FP16 precision the T4 reaches 65 TFLOPS dense against 10 TFLOPS for the GeForce GTX 1660. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the GeForce GTX 1660 or the T4?

Choose the T4 for training and high-throughput inference: it has 6.5x the FP16 throughput of the GeForce GTX 1660. It also carries 10 GB more memory, so larger models fit on one GPU before you shard. The T4 draws 50 W less power, which matters in an air-cooled or power-capped rack.

Which has more memory, the GeForce GTX 1660 or the T4?

The T4 carries 16 GB of memory versus 6 GB for the GeForce GTX 1660. Memory bandwidth is 192 GB/s for the GeForce GTX 1660 and 300 GB/s for the T4.

How much power do the GeForce GTX 1660 and the T4 draw?

The GeForce GTX 1660 is rated at 120 W TDP and the T4 at 70 W. On FP32 throughput per watt, the T4 is the more efficient part.

How much do the GeForce GTX 1660 and the T4 cost to rent?

Live cloud listings tracked by Flopper price the GeForce GTX 1660 from $0.05 per GPU-hour across 1 provider, and the T4 from $0.22 per GPU-hour across 7 providers. The rental section on this page links to every provider, rate and the price history for each GPU.

Where to Rent

NVIDIA GeForce GTX 1660 6GB

Rent from

$0.05 / GPU-hr

Lowest of 1 live listing across 1 provider

See all GeForce GTX 1660 rental prices →

Price history and every provider on the pricing page. Some links are affiliate links.

NVIDIA T4 16GB

Rent from

$0.22 / GPU-hr

Lowest of 16 live listings across 7 providers · median $0.59

See all T4 rental prices →

Price history and every provider on the pricing page. Some links are affiliate links.

Get Comparison Updates

New GPUs added weekly. Be the first to see how they compare.

Open in Full Compare Tool → GeForce GTX 1660 full specs T4 full specs Estimate cluster cost in the calculator →

© 2026 Flopper.io - Compare the GPUs Powering AI