Radeon RX 6500 vs NVIDIA GeForce GTX 1660 SUPER — Specs & Performance Compared

Verdict: The NVIDIA GeForce GTX 1660 SUPER leads on 4 of 5 shared benchmarks (30% in 3DMark Time Spy); the Radeon RX 6500 takes 1 (1% in PassMark G2D Mark). On llama2:7b, the NVIDIA GeForce GTX 1660 SUPER generates 41.4 tokens/s (per llama.cpp GitHub) against 27.8 for the Radeon RX 6500 (per llama.cpp GitHub Discussion #10879), best community run on file for each.

Side-by-side GPU comparison of the Radeon RX 6500 and the NVIDIA GeForce GTX 1660 SUPER. Specs, synthetic benchmarks, AI inference tok/s, and Amazon availability below; each column header links to that part's benchmark page.

AMD · RDNA 2

Radeon RX 6500

4 GB VRAM55W TDP

Full Radeon RX 6500 benchmarks →

NVIDIA · Turing

NVIDIA GeForce GTX 1660 SUPER

6 GB VRAM125W TDP$229 MSRP2019

Full NVIDIA GeForce GTX 1660 SUPER 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	Radeon RX 6500	NVIDIA GeForce GTX 1660 SUPER
vram gb	4	6
vram type	GDDR6	GDDR6
tdp w	55	125
cuda cores	1024	1408
process nm	6	—

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, Notebookcheck, Forbes / Tirias Research, Modders Inc, PCTestBench, HWBOT, UL Solutions 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	Radeon RX 6500	NVIDIA GeForce GTX 1660 SUPER
3DMark Fire Strike (higher is better) Source: 3DMark, Notebookcheck	14,368 points	15,070 points
3DMark Fire Strike (Graphics) (higher is better) Source: Notebookcheck	—	15,855 points
3DMark Fire Strike Extreme (higher is better) Source: Notebookcheck, Forbes / Tirias Research	6,213 points	—
3DMark Fire Strike Ultra (higher is better) Source: Modders Inc, PCTestBench	—	3,299 points
3DMark Port Royal (higher is better) Source: HWBOT	—	1,677 points
3DMark Steel Nomad (higher is better) Source: UL Solutions, Notebookcheck	317 points	1,248 points
3DMark Steel Nomad Light (higher is better) Source: Notebookcheck	—	5,670 points
3DMark Time Spy (higher is better) Source: 3DMark, Notebookcheck, Forbes / Tirias Research, UL Solutions	4,942 points	6,421 points
3DMark Time Spy (Graphics) (higher is better) Source: Notebookcheck	—	5,979 points
3DMark Time Spy Extreme (higher is better) Source: Modders Inc, PCTestBench	—	2,876 points
3DMark Time Spy Graphics (higher is better) Source: Notebookcheck	4,942 points	—
PassMark G2D Mark (higher is better) Source: PassMark	818 pts	807 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.

Radeon RX 6500

llama3.2:3b: 39.8 tok/s (geerlingguy/ai-benchmarks (GitHub))
llama2:7b: 27.8 tok/s (llama.cpp GitHub Discussion #10879)
llama2:7b: 27.8 tok/s (llama.cpp GitHub Discussions)

All Radeon RX 6500 AI benchmarks →

NVIDIA GeForce GTX 1660 SUPER

qwen2.5:0.5b: 63.9 tok/s (LocalScore.ai (Mozilla Builders))
llama2:7b: 41.4 tok/s (llama.cpp GitHub)
llama2:7b: 41.4 tok/s (llama.cpp GitHub)

All NVIDIA GeForce GTX 1660 SUPER AI benchmarks →

Quick answers

Which is faster, the Radeon RX 6500 or the NVIDIA GeForce GTX 1660 SUPER?

The NVIDIA GeForce GTX 1660 SUPER leads on 4 of 5 shared benchmarks (30% in 3DMark Time Spy); the Radeon RX 6500 takes 1 (1% in PassMark G2D Mark).

Which is better for running local LLMs?

On llama2:7b, the NVIDIA GeForce GTX 1660 SUPER generates 41.4 tokens/s (per llama.cpp GitHub) against 27.8 for the Radeon RX 6500 (per llama.cpp GitHub Discussion #10879), best community run on file for each.