Averages 234 FPS at 1440p over our 9-game suite, anchored estimate · high-refresh 1440p, this card pushes fast esports monitors properly
234 Avg FPS Includes estimates
We have not put this card on our bench yet. The numbers below are interpolated from the cards we did measure, on the same suite and the same settings. Across our 9-game suite at 1440p, NVIDIA GeForce RTX 5090 averages 234 FPS. The ceiling is Counter-Strike 2 at 378 FPS; the floor is Alan Wake 2 at 150 FPS, a 2.5x spread that tells you how engine-dependent this class of card is. In practical terms that means high-refresh 1440p, this card pushes fast esports monitors properly. Under load we logged a peak of 552W against the 575W rating.
| Benchmark | Result | 1% Low | VRAM Used | Power | Data |
|---|---|---|---|---|---|
| Cyberpunk 2077 1440p · Ultra | 151 FPS | 121 | 6.75 GB | 546 W | Estimated |
| Red Dead Redemption 2 1440p · Favor Quality | 199 FPS | 154 | 6.57 GB | 535 W | Estimated |
| Alan Wake 2 1440p · High | 150 FPS | 124 | 9.49 GB | 529 W | Estimated |
| Baldur's Gate 3 1440p · Ultra | 293 FPS | 240 | 7 GB | 552 W | Estimated |
| Black Desert Online 1440p · Remastered | 282 FPS | 180 | 5.29 GB | 546 W | Estimated |
| Counter-Strike 2 1440p · Very High | 378 FPS | 207 | 7.13 GB | 405 W | Estimated |
| Diablo 4 1440p · Ultra | 260 FPS | 198 | 9.84 GB | 540 W | Estimated |
| Escape from Tarkov 1440p · Ultra | 226 FPS | 143 | 15.08 GB | 435 W | Estimated |
| The Witcher 3 1440p · Ultra | 166 FPS | 139 | 7.05 GB | 546 W | Estimated |
| Architecture | Blackwell (GB202) |
| CUDA cores | 21,760 |
| VRAM | 32GB GDDR7 |
| Memory bus | 512-bit |
| Memory bandwidth | 1792 GB/s |
| Boost clock | 2,407 MHz |
| TDP | 575 W |
| Process | 5nm |
| Interface | PCIe 5.0 x16 |
| Release date | 2025-01-30 |
| Launch MSRP | $1,999 |
NVIDIA GeForce RTX 5090 averages 234 FPS at 1440p on our suite. We have not put this card on our bench yet. The numbers below are interpolated from the cards we did measure, on the same suite and the same settings.
100% = this card, Gaming headline metric (Avg FPS). #1 of 82 desktop cards in this vertical.
| GPU | Relative | % | Avg FPS |
|---|---|---|---|
| NVIDIA GeForce RTX 5090 | 100% | 234 | |
| NVIDIA GeForce RTX 4090 | 85% | 198 | |
| GeForce RTX 5080 | 79% | 185 | |
| GeForce RTX 4080 Super | 71% | 167 | |
| AMD Radeon RX 7900 XTX | 70% | 164 |
Same card, other workloads: NVIDIA GeForce RTX 5090 AI benchmarks, LLM tokens/sec, image generation & VRAM fit
| Transistors | 92,200 million |
| Die size | 750 mm² |
| Process node | 4 nm |
| Fabricated by | TSMC |
| Transistor density | 122.9 million per mm² |
Denser than 96% of the 76 cards we have silicon data for. Density is the clearest measure of what a process node bought: a card that gained it without growing the die got its speed from the fab rather than the architecture.
Silicon figures from Wikipedia (CC BY-SA 4.0). Benchmarks on this page are our own. Compare every chip.
Whole-job timings, composed from our measured per-model results on this card.
| Workflow | Time | Energy | Basis |
|---|---|---|---|
| Full codebase review | 6.7 min | 13.03 Wh | measured |
| 24-frame storyboard | 12.5 min | 21.46 Wh | all 2 stages measured |
Can't run: 20 long-form articles (needs Llama 3.3 70B).
This card is $1,999 to buy. The cheapest listed rate on Vast.ai is $0.321/hour, but that is the floor: we budget $0.385/hour, a 20% premium, because idle time, storage and unavailable cheap instances all land on the same bill. At that rate buying wins after 5,190 GPU-hours. Below it you are paying for idle silicon.
| How you would use it | GPU-hours a year | Rental cost a year | Time to break even |
|---|---|---|---|
| 2 hours a day, hobby | 730 | $281 | 7.1 years |
| 8 hours a day, working on it | 2,920 | $1,125 | 1.8 years |
| 24/7, always-on agent | 8,760 | $3,374 | 7.1 months |
At hobby usage this card is very unlikely to pay for itself before it is superseded. Rent it. Rental figures include a 20% premium over the cheapest listed rate. Ignores electricity, resale and the fact that a rented card can be a newer one tomorrow.
Cheapest of the RunPod and Vast on-demand rates we see, sampled daily. Spot and interruptible pricing runs lower.