NVIDIA GeForce RTX 4090 vs NVIDIA GeForce RTX 5070 Ti — Specs & Performance Compared

Side-by-side comparison of 2 GPU parts: NVIDIA GeForce RTX 4090 vs NVIDIA GeForce RTX 5070 Ti. Release years: 2022, 2025. MSRP range: $1,599 · $749. Specs, synthetic benchmarks, AI inference tok/s, and Amazon availability — click into any column header for the per-SKU benchmark page.

vs

*Price sourced from Amazon.com. Last updated 2026-05-27. Price and availability subject to change.

Specs side-by-side

SpecNVIDIA GeForce RTX 4090NVIDIA GeForce RTX 5070 Ti
vram gb 2416
vram type GDDR6XGDDR7
tdp w 450300
cuda cores 163848960

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.

BenchmarkNVIDIA GeForce RTX 4090NVIDIA GeForce RTX 5070 Ti
3DMark Speed Way —7,708 points
3DMark Time Spy —27,949 points
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 1,302 pts1,329 pts
PassMark G3D Mark 38,066 pts32,422 pts
Tom's Hardware GPU Hierarchy 2 rank812 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 4090

  • llama3:8b: 440.0 tok/s
  • Llama 2 7B: 194.0 tok/s
  • Llama 3.1 8B: 165.0 tok/s

All NVIDIA GeForce RTX 4090 AI benchmarks →

NVIDIA GeForce RTX 5070 Ti

  • qwen3:0.6b: 47.1 tok/s
  • qwen3:235b: 11.0 tok/s
  • gemma:26b: 5.0 tok/s

All NVIDIA GeForce RTX 5070 Ti AI benchmarks →

Keep exploring