Skip to main content

NVIDIA GeForce GTX 1660 vs NVIDIA GeForce RTX 3080 Ti — Specs & Performance Compared

Verdict: The NVIDIA GeForce RTX 3080 Ti is ahead of the NVIDIA GeForce GTX 1660 on all 4 shared benchmarks on file, by 41% to 387%, including 247% in 3DMark Time Spy (19,179 vs 5,521). On llama3.1:8b, the NVIDIA GeForce RTX 3080 Ti generates 89.7 tokens/s (per LocalScore AI) against 16.7 for the NVIDIA GeForce GTX 1660 (per DatabaseMart), best community run on file for each.

Side-by-side GPU comparison of the NVIDIA GeForce GTX 1660 and the NVIDIA GeForce RTX 3080 Ti. Released 2019 (NVIDIA GeForce GTX 1660), 2021 (NVIDIA GeForce RTX 3080 Ti). MSRP range: $219 · $1,199. Specs, synthetic benchmarks, AI inference tok/s, and Amazon availability below; each column header links to that part's benchmark page.

vs

*Price sourced from Amazon.com. Price and availability subject to change.

Where to buy

A listing for each part; the current price and stock are on the retailer's page.

Specs side-by-side

SpecNVIDIA GeForce GTX 1660NVIDIA GeForce RTX 3080 Ti
vram gb 612
vram type GDDR5GDDR6X
tdp w 120350
cuda cores 140810240

Synthetic benchmarks

Each row says whether a higher or a lower number is better (ranks and times are lower-is-better). Scores come from 3DMark, HWBOT, ComputerBase, TopCPU.net, HWBOT Community, CpuTronic, Notebookcheck, Legit Reviews, PC Perspective, GPU-Monkey, PassMark and AskGeek.io; each row links its sources, and where they differ the cell shows their median. Empty cells mean we don't yet have that benchmark on file for the SKU.

BenchmarkNVIDIA GeForce GTX 1660NVIDIA GeForce RTX 3080 Ti
3DMark Fire Strike (higher is better)
Source: 3DMark		 12,365 points—
3DMark Port Royal (higher is better)
Source: 3DMark, HWBOT, ComputerBase		 —14,254 points
3DMark Speed Way (higher is better)
Source: 3DMark, TopCPU.net, HWBOT Community, ComputerBase		 —5,441 points
3DMark Steel Nomad (higher is better)
Source: 3DMark, CpuTronic, ComputerBase		 1,047 points5,094 points
3DMark Steel Nomad Light (higher is better)
Source: ComputerBase		 —21,907 points
3DMark Time Spy (higher is better)
Source: 3DMark, Notebookcheck, TopCPU.net, CpuTronic, Legit Reviews		 5,521 points19,179 points
3DMark Time Spy (GPU score) (higher is better)
Source: ComputerBase		 —18,680 points
3DMark Time Spy Extreme (higher is better)
Source: TopCPU.net, PC Perspective		 —9,714 points
3DMark Time Spy Graphics (higher is better)
Source: GPU-Monkey		 5,395 points—
PassMark G2D Mark (higher is better)
Source: PassMark		 776 pts1,095 pts
PassMark G3D Mark (higher is better)
Source: PassMark, AskGeek.io		 11,618 pts26,774 pts

AI inference (tokens/sec)

Top community-reported tokens-per-second results for popular LLMs whose weights fit the card's memory, each linked to its source. See the per-SKU benchmark page for the full set including quantization and prompt length.

NVIDIA GeForce GTX 1660

All NVIDIA GeForce GTX 1660 AI benchmarks →

NVIDIA GeForce RTX 3080 Ti

All NVIDIA GeForce RTX 3080 Ti AI benchmarks →

Quick answers

Which is faster, the NVIDIA GeForce GTX 1660 or the NVIDIA GeForce RTX 3080 Ti?

The NVIDIA GeForce RTX 3080 Ti is ahead of the NVIDIA GeForce GTX 1660 on all 4 shared benchmarks on file, by 41% to 387%, including 247% in 3DMark Time Spy (19,179 vs 5,521).

Which is better for running local LLMs?

On llama3.1:8b, the NVIDIA GeForce RTX 3080 Ti generates 89.7 tokens/s (per LocalScore AI) against 16.7 for the NVIDIA GeForce GTX 1660 (per DatabaseMart), best community run on file for each.

What did the NVIDIA GeForce GTX 1660 and the NVIDIA GeForce RTX 3080 Ti cost at launch?

The NVIDIA GeForce GTX 1660 launched at a $219 MSRP and the NVIDIA GeForce RTX 3080 Ti at $1,199. Street prices drift from launch pricing; the Where to buy section links current listings.

Keep exploring

More guides & deep dives from the SpecPicks archive

Browse all articles & guides →

More reviews from the SpecPicks archive

Browse all reviews →

More buying guides from SpecPicks

Browse all buying guides →

Hardware benchmark data on SpecPicks

All benchmarks →