Averages 125 FPS at 1440p over our 9-game suite, anchored estimate · smooth 100+ FPS 1440p gaming across demanding AAA titles
125 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 4070 Super averages 125 FPS. The ceiling is Counter-Strike 2 at 206 FPS; the floor is Alan Wake 2 at 81 FPS, a 2.5x 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 220W against the 220W rating.
Anchored estimate, this card hasn't been through our test bench yet. Its numbers are interpolated from the cards that have, on the same suite and the same settings, and they'll be replaced with measured results once it runs.
| Benchmark | Result | 1% Low | VRAM Used | Power | Data |
|---|---|---|---|---|---|
| Alan Wake 2 1440p · Ultra | 81 FPS | 68 | 9.36 GB | 207 W | Estimated |
| Baldur's Gate 3 1440p · Ultra | 160 FPS | 126 | 6.74 GB | 220 W | Estimated |
| Black Desert Online 1440p · Ultra | 145 FPS | 84 | 4.91 GB | 200 W | Estimated |
| Counter-Strike 2 1440p · Ultra | 206 FPS | 113 | 5.98 GB | 195 W | Estimated |
| Cyberpunk 2077 1440p · Ultra | 95 FPS | 76 | 6.73 GB | 219 W | Estimated |
| Diablo 4 1440p · Ultra | 118 FPS | 84 | 9.84 GB | 211 W | Estimated |
| Escape from Tarkov 1440p · Ultra | 123 FPS | 92 | 11.58 GB | 217 W | Estimated |
| Red Dead Redemption 2 1440p · Ultra | 101 FPS | 84 | 6.2 GB | 209 W | Estimated |
| The Witcher 3 1440p · Ultra | 99 FPS | 78 | 5.43 GB | 214 W | Estimated |
| Architecture | Ada Lovelace |
| CUDA cores | 7,168 |
| VRAM | 12GB GDDR6X |
| Memory bus | 192-bit |
| Memory bandwidth | 504 GB/s |
| Boost clock | 2,475 MHz |
| TDP | 220 W |
| Process | 4nm (TSMC 4N) |
| Interface | PCIe 4.0 x16 |
| Release date | 2024-01-17 |
| Launch MSRP | $599 |
NVIDIA GeForce RTX 4070 Super averages 125 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). #19 of 82 desktop cards in this vertical.
| GPU | Relative | % | Avg FPS |
|---|---|---|---|
| AMD Radeon RX 7900 GRE | 105% | 131 | |
| NVIDIA GeForce RTX 3080 Ti | 104% | 130 | |
| AMD Radeon RX 9070 GRE | 101% | 126 | |
| NVIDIA GeForce RTX 3080 12GB | 100% | 125 | |
| NVIDIA GeForce RTX 4070 Super | 100% | 125 | |
| AMD Radeon RX 6900 XT | 98% | 122 | |
| AMD Radeon RX 9070 | 97% | 121 | |
| AMD Radeon RX 7800 XT | 94% | 118 | |
| GeForce RTX 5070 | 90% | 112 |
Same card, other workloads: NVIDIA GeForce RTX 4070 Super AI benchmarks, LLM tokens/sec, image generation & VRAM fit
| Transistors | 35,800 million |
| Die size | 294.5 mm² |
| Process node | 4 nm |
| Fabricated by | TSMC |
| Transistor density | 121.6 million per mm² |
Denser than 94% 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 |
|---|---|---|---|
| Full codebase review | 19.5 min | 46.03 Wh | measured |
Can't run: Animate a batch of images (needs Wan 2.2 TI2V-5B (image to video)), 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), Short social clips (needs Qwen3 32B), 60-second AI short film (needs Qwen3 32B), 24-frame storyboard (needs Qwen3 32B), 6-panel comic page (needs Qwen3 32B), Long-form article batch (needs Llama 3.3 70B).
This card is $599 to buy. The cheapest listed rate on Vast.ai is $0.130/hour, but that is the floor: we budget $0.156/hour, a 20% premium, because idle time, storage and unavailable cheap instances all land on the same bill. At that rate buying wins after 3,840 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 | $114 | 5.3 years |
| 8 hours a day, working on it | 2,920 | $456 | 1.3 years |
| 24/7, always-on agent | 8,760 | $1,367 | 5.3 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.