132 FPS at 1440p across 9 games (anchored estimate) · smooth 100+ FPS 1440p gaming across demanding AAA titles
132 Avg FPS Includes estimates
Nothing here is a measurement of this card. It is an anchored estimate built from the cards we have run ourselves, on the identical suite. Across our 9-game suite at 1440p, NVIDIA GeForce RTX 3090 averages 132 FPS. The ceiling is Counter-Strike 2 at 229 FPS; the floor is Alan Wake 2 at 81 FPS, a 2.8x spread that tells you how engine-dependent this class of card is. In practical terms that means smooth 100+ FPS 1440p gaming across demanding AAA titles. Under load we logged a peak of 336W against the 350W rating.
| Benchmark | Result | 1% Low | VRAM Used | Power | Data |
|---|---|---|---|---|---|
| Cyberpunk 2077 1440p · Ultra | 101 FPS | 81 | 6.75 GB | 332 W | Estimated |
| Red Dead Redemption 2 1440p · Favor Quality | 111 FPS | 86 | 6.57 GB | 326 W | Estimated |
| Alan Wake 2 1440p · High | 81 FPS | 67 | 9.49 GB | 322 W | Estimated |
| Baldur's Gate 3 1440p · Ultra | 156 FPS | 128 | 7 GB | 336 W | Estimated |
| Black Desert Online 1440p · Remastered | 165 FPS | 105 | 5.29 GB | 332 W | Estimated |
| Counter-Strike 2 1440p · Very High | 229 FPS | 126 | 7.13 GB | 260 W | Estimated |
| Diablo 4 1440p · Ultra | 136 FPS | 104 | 9.84 GB | 329 W | Estimated |
| Escape from Tarkov 1440p · Ultra | 124 FPS | 90 | 15.08 GB | 280 W | Estimated |
| The Witcher 3 1440p · Ultra | 89 FPS | 74 | 7.05 GB | 332 W | Estimated |
| Architecture | Ampere (GA102) |
| CUDA cores | 10,496 |
| VRAM | 24GB GDDR6X |
| Memory bus | 384-bit |
| Memory bandwidth | 936.2 GB/s |
| Boost clock | 1,695 MHz |
| TDP | 350 W |
| Process | 8nm (Samsung) |
| Interface | PCIe 4.0 x16 |
| Release date | 2020-09-24 |
| Launch MSRP | $1,499 |
NVIDIA GeForce RTX 3090 averages 132 FPS at 1440p on our suite. Nothing here is a measurement of this card. It is an anchored estimate built from the cards we have run ourselves, on the identical suite.
100% = this card, Gaming headline metric (Avg FPS). #14 of 82 desktop cards in this vertical.
| GPU | Relative | % | Avg FPS |
|---|---|---|---|
| GeForce RTX 5070 Ti | 106% | 140 | |
| AMD Radeon RX 9070 XT | 104% | 137 | |
| NVIDIA GeForce RTX 4070 Ti | 103% | 136 | |
| AMD Radeon RX 6950 XT | 100% | 132 | |
| NVIDIA GeForce RTX 3090 | 100% | 132 | |
| AMD Radeon RX 7900 GRE | 99% | 131 | |
| NVIDIA GeForce RTX 3080 Ti | 98% | 130 | |
| AMD Radeon RX 9070 GRE | 95% | 126 | |
| NVIDIA GeForce RTX 3080 12GB | 95% | 125 |
Same card, other workloads: NVIDIA GeForce RTX 3090 AI benchmarks, LLM tokens/sec, image generation & VRAM fit
| Transistors | 28,300 million |
| Die size | 628.4 mm² |
| Process node | 8 nm |
| Fabricated by | Samsung |
| Transistor density | 45 million per mm² |
Denser than 81% of the 746 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 |
|---|---|---|---|
| 24-frame storyboard | 8.3 min | 37.34 Wh | all 2 stages measured |
| Full codebase review | 12.7 min | 37.63 Wh | measured |
| 60-second AI short film | 15.2 min | 57.1 Wh | all 3 stages measured |
| Animate a batch of images | 33.1 min | 128.43 Wh | measured |
| Short social clips | 42.4 min | 209.99 Wh | all 3 stages measured |
Can't run: Product photo shoot (needs FLUX.1 Kontext dev), Photo restoration batch (needs FLUX.1 Kontext dev), Restore and enlarge photos (needs FLUX.1 Kontext dev), Character sheet, 12 poses (needs FLUX.1 dev), 6-panel comic page (needs FLUX.1 dev), Long-form article batch (needs Llama 3.3 70B).
This card is $1,499 to buy. The cheapest listed rate on Vast.ai is $0.143/hour, but that is the floor: we budget $0.172/hour, a 20% premium, because idle time, storage and unavailable cheap instances all land on the same bill. At that rate buying wins after 8,735 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 | $125 | 12.0 years |
| 8 hours a day, working on it | 2,920 | $501 | 3.0 years |
| 24/7, always-on agent | 8,760 | $1,503 | 12.0 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.