Radeon RX 7900 GRE vs NVIDIA GeForce RTX 3060 — Specs & Performance Compared

Verdict: The Radeon RX 7900 GRE is ahead of the NVIDIA GeForce RTX 3060 on all 6 shared benchmarks on file, by 23% to 143%, including 143% in 3DMark Time Spy (21,296 vs 8,747). On llama2:7b, the Radeon RX 7900 GRE generates 116.1 tokens/s (per llama.cpp GitHub Discussion #10879) against 80.6 for the NVIDIA GeForce RTX 3060 (per llama.cpp GitHub Discussion #10879), best community run on file for each.

Side-by-side GPU comparison of the Radeon RX 7900 GRE and the NVIDIA GeForce RTX 3060. Specs, synthetic benchmarks, AI inference tok/s, and Amazon availability below; each column header links to that part's benchmark page.

AMD · RDNA 3

Radeon RX 7900 GRE

16 GB VRAM

Full Radeon RX 7900 GRE benchmarks →

NVIDIA · Ampere

NVIDIA GeForce RTX 3060

12 GB VRAM170W TDP$329 MSRP2021

Full NVIDIA GeForce RTX 3060 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 7900 GRE	NVIDIA GeForce RTX 3060
vram gb	16	12
vram type	—	GDDR6
tdp w	—	170
cuda cores	—	3584

Synthetic benchmarks

Each row says whether a higher or a lower number is better (ranks and times are lower-is-better). Scores come from Tom's Hardware, 3DMark, LANOC, WCCFTech, Legit Reviews, Overclocking.com, TopCPU.net, CpuTronic, HWBOT, TechPowerUp, PCGamesN 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 7900 GRE	NVIDIA GeForce RTX 3060
3DMark Fire Strike (higher is better) Source: Tom's Hardware, 3DMark, LANOC	51,358 pts	21,653 points
3DMark Port Royal (higher is better) Source: WCCFTech, Legit Reviews, Overclocking.com, 3DMark	12,041 points	5,074 points
3DMark Speed Way (higher is better) Source: TopCPU.net, 3DMark, Overclocking.com, LANOC	4,013 points	2,170 points
3DMark Steel Nomad (higher is better) Source: 3DMark, CpuTronic	4,802 points	1,984 points
3DMark Steel Nomad (Vulkan) (higher is better) Source: HWBOT	5,394 points	—
3DMark Steel Nomad DX12 Graphics Score (higher is better) Source: 3DMark	—	1,978 points
3DMark Time Spy (higher is better) Source: TechPowerUp, TopCPU.net, Overclocking.com, LANOC, 3DMark	21,296 pts	8,747 points
3DMark Time Spy (overall score) (higher is better) Source: Legit Reviews	—	9,755 points
3DMark Time Spy Extreme (higher is better) Source: Overclocking.com, PCGamesN	10,249 points	—
PassMark G2D Mark (higher is better) Source: PassMark	1,208 pts	984 pts
PassMark G3D Mark (higher is better) Source: PassMark	27,385 pts	16,969 pts
Tom's Hardware GPU Hierarchy (lower is better) Source: Tom's Hardware	670 rank	12 rank

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 7900 GRE

llama2:7b: 116.1 tok/s (llama.cpp GitHub Discussion #10879)
llama2:7b: 116.1 tok/s (llama.cpp GitHub Discussion #10879)
llama2:7b: 96.1 tok/s (llama.cpp GitHub Discussion #15021)

All Radeon RX 7900 GRE AI benchmarks →

NVIDIA GeForce RTX 3060

llama3.2:1b: 184.0 tok/s (LocalScore.ai)
llama3.2:3b: 128.3 tok/s (tyolab.com)
llama3.2:3b: 128.3 tok/s (tyolab.com)

All NVIDIA GeForce RTX 3060 AI benchmarks →

Quick answers

Which is faster, the Radeon RX 7900 GRE or the NVIDIA GeForce RTX 3060?

The Radeon RX 7900 GRE is ahead of the NVIDIA GeForce RTX 3060 on all 6 shared benchmarks on file, by 23% to 143%, including 143% in 3DMark Time Spy (21,296 vs 8,747).

Which is better for running local LLMs?

On llama2:7b, the Radeon RX 7900 GRE generates 116.1 tokens/s (per llama.cpp GitHub Discussion #10879) against 80.6 for the NVIDIA GeForce RTX 3060 (per llama.cpp GitHub Discussion #10879), best community run on file for each.