NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 4090 — Specs & Performance Compared
Side-by-side comparison of 2 GPU parts: NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 4090. Release years: 2020, 2022. MSRP range: $1,499 · $1,599. Specs, synthetic benchmarks, AI inference tok/s, and Amazon availability — click into any column header for the per-SKU benchmark page.
NVIDIA · Ampere
24 GB VRAM350W TDP$1,499 MSRP2020
Full NVIDIA GeForce RTX 3090 benchmarks →
vs
NVIDIA · Ada Lovelace
NVIDIA GeForce RTX 4090
24 GB VRAM450W TDP$1,599 MSRP2022
Full NVIDIA GeForce RTX 4090 benchmarks →
*Price sourced from Amazon.com. Last updated 2026-05-27. Price and availability subject to change.
Specs side-by-side
| Spec | NVIDIA GeForce RTX 3090 | NVIDIA GeForce RTX 4090 |
|---|---|---|
| vram gb | 24 | 24 |
| vram type | GDDR6X | GDDR6X |
| tdp w | 350 | 450 |
| cuda cores | 10496 | 16384 |
Synthetic benchmarks
Higher 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.
| Benchmark | NVIDIA GeForce RTX 3090 | NVIDIA GeForce RTX 4090 |
|---|---|---|
| 3DMark Time Spy Extreme | — | 38,450 pts |
| 3DMark Time Spy Extreme (Graphics) | — | 19,000 pts |
| 3DMark Time Spy GPU | — | 35,200 pts |
| Deep Learning Benchmark (ResNet-50) | — | 128,000 images/sec |
| PassMark G2D Mark | 1,069 pts | 1,302 pts |
| PassMark G3D Mark | 26,546 points | 38,066 pts |
| Tom's Hardware GPU Hierarchy | — | 2 rank |
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
- qwen3:35b-a3b: 135.7 tok/s
- qwen3:0.6b: 47.1 tok/s
- qwen2.5:32b: 18.0 tok/s
NVIDIA GeForce RTX 4090
- llama3:8b: 440.0 tok/s
- Llama 2 7B: 194.0 tok/s
- Llama 3.1 8B: 165.0 tok/s