Skip to main content

NVIDIA GeForce RTX 3090 vs Radeon RX 7900 XTX — Specs & Performance Compared

Side-by-side comparison of 2 GPU parts: NVIDIA GeForce RTX 3090 vs Radeon RX 7900 XTX. Specs, synthetic benchmarks, AI inference tok/s, and Amazon availability — click into any column header for the per-SKU benchmark page.

Verdict: The Radeon RX 7900 XTX is ahead of the NVIDIA GeForce RTX 3090 on all 6 shared benchmarks on file, by 4% to 37% (37% in 3DMark Speed Way). On llama3:70b, the Radeon RX 7900 XTX generates 13.4 tokens/s against 10.0 for the NVIDIA GeForce RTX 3090 (best community run on file for each).

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 RTX 3090Radeon RX 7900 XTX
vram gb 2424
vram type GDDR6X—
tdp w 350—
cuda cores 10496—

Synthetic benchmarks

Each row says whether a higher or a lower number is better (ranks and times are lower-is-better). Per-row scores come from public benchmark databases (PassMark, TechPowerUp, Geekbench, Cinebench). Empty cells mean we don't yet have that benchmark on file for the SKU.

BenchmarkNVIDIA GeForce RTX 3090Radeon RX 7900 XTX
3DMark Port Royal (higher is better) 15,039 points15,715 points
3DMark Speed Way (higher is better) 5,075 points6,953 points
3DMark Steel Nomad (higher is better) 5,229 points6,862 points
3DMark Time Spy (higher is better) 18,824 points25,214 pts
3DMark Time Spy (combined) (higher is better) —27,934 points
3DMark Time Spy (GPU) (higher is better) —30,139 points
3DMark Time Spy Extreme (higher is better) 9,800 points—
PassMark G2D Mark (higher is better) 1,069 pts1,285 pts
PassMark G3D Mark (higher is better) 26,548 pts31,409 pts
Port Royal (Ray Tracing) (higher is better) —14,200 pts
Tom's Hardware GPU Hierarchy (lower is better) —959 rank
Unigine Superposition 4K Optimized (higher is better) —21,192 points

AI inference (tokens/sec)

Top community-reported tokens-per-second results for popular LLMs. See the per-SKU benchmark page for the full set including quantization, prompt length, and source citations.

NVIDIA GeForce RTX 3090

  • llama3.2:1b: 267.0 tok/s
  • qwen3:35b-a3b: 135.7 tok/s
  • qwen3.6-35b-a3b: 120.0 tok/s

All NVIDIA GeForce RTX 3090 AI benchmarks →

Radeon RX 7900 XTX

  • llama2:7b: 170.1 tok/s
  • llama3.2:3b: 145.0 tok/s
  • llama3.2:3b: 145.0 tok/s

All Radeon RX 7900 XTX AI benchmarks →

Quick answers

Which is faster, the NVIDIA GeForce RTX 3090 or the Radeon RX 7900 XTX?

The Radeon RX 7900 XTX is ahead of the NVIDIA GeForce RTX 3090 on all 6 shared benchmarks on file, by 4% to 37% (37% in 3DMark Speed Way).

Which is better for running local LLMs?

On llama3:70b, the Radeon RX 7900 XTX generates 13.4 tokens/s against 10.0 for the NVIDIA GeForce RTX 3090 (best community run on file for each).

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 →