NVIDIA · Blackwell
NVIDIA GeForce RTX 5090
32 GB VRAM575W TDP$1,999 MSRP2025
Full NVIDIA GeForce RTX 5090 benchmarks →
NVIDIA GeForce RTX 5090 vs Apple M3 Ultra — Specs & Performance Compared
Side-by-side comparison of 2 hardware parts: NVIDIA GeForce RTX 5090 vs Apple M3 Ultra. All released in 2025. Specs, synthetic benchmarks, AI inference tok/s, and Amazon availability — click into any column header for the per-SKU benchmark page.
*Price sourced from Amazon.com. Last updated 2026-05-27. Price and availability subject to change.
Specs side-by-side
| Spec | NVIDIA GeForce RTX 5090 | Apple M3 Ultra |
|---|---|---|
| vram gb | 32 | — |
| vram type | GDDR7 | — |
| tdp w | 575 | — |
| cuda cores | 21760 | — |
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 5090 | Apple M3 Ultra |
|---|---|---|
| 3DMark Port Royal | 36,667 points | — |
| 3DMark Speed Way | 14,444 points | — |
| 3DMark Steel Nomad (4K) | 14,133 points | — |
| 3DMark Time Spy | 32,500 pts | — |
| Geekbench 6 Metal (GPU) | — | 259,668 points |
| Geekbench 6 Multi-Core | — | 27,759 points |
| Geekbench 6 Single-Core | — | 3,201 points |
| PassMark CPU Mark | — | 72,769 pts |
| PassMark CPU Mark Single Thread | — | 5,048 points |
| PassMark G2D Mark | 1,412 pts | — |
| PassMark G3D Mark | 38,935 pts | — |
| PassMark Single Thread | — | 5,048 pts |
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 5090
- Qwen2.5-Coder-7B-Instruct: 5841.0 tok/s
- Llama 3.1 8B FP8: 420.0 tok/s
- Llama 2 7B: 263.6 tok/s
Apple M3 Ultra
- deepseekr1:32b: 100.0 tok/s
- qwen3:235b: 31.9 tok/s
- qwen3:0.6b: 31.0 tok/s