NVIDIA GeForce GTX 1650 vs NVIDIA GeForce GTX 1660 Ti — Specs & Performance Compared

Verdict: The NVIDIA GeForce GTX 1660 Ti is ahead of the NVIDIA GeForce GTX 1650 on all 5 shared benchmarks on file, by 40% to 308%, including 67% in 3DMark Time Spy (6,314 vs 3,773). On qwen3:0.6b, both reach about 47.1 tokens/s (per LocalLLaMA; per LocalLLaMA).

Side-by-side GPU comparison of the NVIDIA GeForce GTX 1650 and the NVIDIA GeForce GTX 1660 Ti. Both released in 2019. MSRP range: $149 · $279. Specs, synthetic benchmarks, AI inference tok/s, and Amazon availability below; each column header links to that part's benchmark page.

NVIDIA · Turing

NVIDIA GeForce GTX 1650

4 GB VRAM75W TDP$149 MSRP2019

Full NVIDIA GeForce GTX 1650 benchmarks →

NVIDIA · Turing

NVIDIA GeForce GTX 1660 Ti

6 GB VRAM120W TDP$279 MSRP2019

Full NVIDIA GeForce GTX 1660 Ti benchmarks →

*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

Spec	NVIDIA GeForce GTX 1650	NVIDIA GeForce GTX 1660 Ti
vram gb	4	6
vram type	GDDR5	GDDR6
tdp w	75	120
cuda cores	896	1536

Synthetic benchmarks

Each row says whether a higher or a lower number is better (ranks and times are lower-is-better). Scores come from Notebookcheck, 3DMark, Modders Inc, Legit Reviews, PCGamesN, TopCPU, HEXUS and PassMark; 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.

Benchmark	NVIDIA GeForce GTX 1650	NVIDIA GeForce GTX 1660 Ti
3DMark Fire Strike (higher is better) Source: Notebookcheck, 3DMark	9,068 points	14,413 points
3DMark Fire Strike Ultra (higher is better) Source: Modders Inc	—	3,368 points
3DMark Steel Nomad (higher is better) Source: 3DMark, Notebookcheck	320 points	1,306 points
3DMark Time Spy (higher is better) Source: Legit Reviews, 3DMark, PCGamesN, Notebookcheck, TopCPU, HEXUS	3,773 points	6,314 points
3DMark Time Spy Extreme (higher is better) Source: Modders Inc	—	2,878 points
PassMark G2D Mark (higher is better) Source: PassMark	552 pts	776 pts
PassMark G3D Mark (higher is better) Source: PassMark	7,870 pts	12,615 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 1650

qwen3:0.6b: 47.1 tok/s (LocalLLaMA)
gemma-4-e2b-it:q4_0: 40.0 tok/s (Medium (personal benchmark))
llama3.2:1b: 14.0 tok/s (WillItRunAI)

All NVIDIA GeForce GTX 1650 AI benchmarks →

NVIDIA GeForce GTX 1660 Ti

llama2:7b: 56.6 tok/s (llama.cpp GitHub Discussions #10879)
qwen3:0.6b: 47.1 tok/s (LocalLLaMA)
llama2:7b: 41.4 tok/s (llama.cpp GitHub Discussions)

All NVIDIA GeForce GTX 1660 Ti AI benchmarks →

Quick answers

Which is faster, the NVIDIA GeForce GTX 1650 or the NVIDIA GeForce GTX 1660 Ti?

The NVIDIA GeForce GTX 1660 Ti is ahead of the NVIDIA GeForce GTX 1650 on all 5 shared benchmarks on file, by 40% to 308%, including 67% in 3DMark Time Spy (6,314 vs 3,773).

Which is better for running local LLMs?

On qwen3:0.6b, both reach about 47.1 tokens/s (per LocalLLaMA; per LocalLLaMA).

What did the NVIDIA GeForce GTX 1650 and the NVIDIA GeForce GTX 1660 Ti cost at launch?

The NVIDIA GeForce GTX 1650 launched at a $149 MSRP and the NVIDIA GeForce GTX 1660 Ti at $279. Street prices drift from launch pricing; the Where to buy section links current listings.