82 FPS average at 1440p across 12 games, first-party measured · solid 60+ FPS 1440p gaming, with headroom in lighter titles
82 Avg FPS ✓ Measured
These are our own numbers. 12 games, one bench, one card, with the capture published for each result. Across our 12-game suite at 1440p, NVIDIA GeForce RTX 3070 Founders Edition averages 82 FPS. The ceiling is F1 2022 at 147 FPS; the floor is The Last of Us Part I at 51 FPS, a 2.9x spread that tells you how engine-dependent this class of card is. In practical terms that means solid 60+ FPS 1440p gaming, with headroom in lighter titles. Under load we logged a peak of 275W against the 220W rating.
F1 2022's 1% low came in at 54% of its average, the average says smooth, the lows say otherwise. 7.83GB of the 8GB used in Forza; this card is at its VRAM ceiling in modern titles. These gaming numbers came off my own test bench: a Ryzen 7 7800X3D system, identical settings on every card, with a capture kept for every run. Everything here was double-checked before it went up.
| Benchmark | Result | 1% Low | VRAM Used | Power | Data |
|---|---|---|---|---|---|
| Atomic Heart 1440p · Atomic | 110 FPS | 74 | 5.94 GB | 236 W | ✓ Measured |
| Call of Duty: MW2 1440p · Extreme | 70 FPS | 56 | 7.03 GB | 227 W | ✓ Measured |
| Cyberpunk 2077 1440p · Ultra | 76 FPS | 64 | 5.46 GB | 265 W | ✓ Measured |
| Dying Light 2 1440p · High Quality | 82 FPS | 72 | 4.05 GB | 249 W | ✓ Measured |
| Elden Ring 1440p · Maximum | 84 FPS | 67 | 4.08 GB | 216 W | ✓ Measured |
| F1 2022 1440p · Ultra High | 147 FPS | 79 | 7.1 GB | 261 W | ✓ Measured |
| Forza Horizon 5 1440p · Extreme | 87 FPS | 74 | 7.83 GB | 217 W | ✓ Measured |
| Hogwarts Legacy 1440p · Ultra | 64 FPS | 35 | 7.01 GB | 242 W | ✓ Measured |
| Red Dead Redemption 2 1440p · Favor Quality | 81 FPS | 60 | 6.26 GB | 254 W | ✓ Measured |
| Resident Evil 4 Remake 1440p · Maximum | 85 FPS | 66 | 7.59 GB | 270 W | ✓ Measured |
| Star Wars Jedi: Survivor 1440p · Epic | 51 FPS | 38 | 7.23 GB | 275 W | ✓ Measured |
| The Last of Us Part I 1440p · Ultra | 51 FPS | 35 | 7.44 GB | 222 W | ✓ Measured |
| Architecture | Ampere (GA104) |
| CUDA cores | 5,888 |
| VRAM | 8GB GDDR6 |
| Memory bus | 256-bit |
| Memory bandwidth | 448 GB/s |
| Boost clock | 1,725 MHz |
| TDP | 220 W |
| Process | 8nm (Samsung 8N) |
| Interface | PCIe 4.0 x16 |
| Release date | 2020-10-29 |
| Launch MSRP | $499 |
NVIDIA GeForce RTX 3070 Founders Edition averages 82 FPS at 1440p on our suite. These are our own numbers. 12 games, one bench, one card, with the capture published for each result.
100% = this card, Gaming headline metric (Avg FPS). #35 of 82 desktop cards in this vertical.
| GPU | Relative | % | Avg FPS |
|---|---|---|---|
| AMD Radeon RX 6800 | 109% | 89 | |
| NVIDIA GeForce RTX 2080 Super | 104% | 85 | |
| GeForce RTX 5060 Ti | 102% | 84 | |
| NVIDIA GeForce RTX 4060 Ti | 101% | 83 | |
| NVIDIA GeForce RTX 3070 Founders Edition | 100% | 82 | |
| NVIDIA GeForce RTX 2080 Founders Edition | 98% | 80 | |
| AMD Radeon RX 9060 | 95% | 78 | |
| AMD Radeon RX 9060 XT | 94% | 77 | |
| NVIDIA TITAN V | 93% | 76 |
Same card, other workloads: NVIDIA GeForce RTX 3070 Founders Edition AI benchmarks, LLM tokens/sec, image generation & VRAM fit
| Transistors | 17,400 million |
| Die size | 392.5 mm² |
| Fabricated by | Samsung |
| Transistor density | 44.3 million per mm² |
Denser than 42% 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.
Can't run: 60-second AI short film (needs Qwen3 32B), 60-second AI short film, narrated (needs Qwen3 32B), 10 short social clips (needs Qwen3 32B), 40-product photo shoot (needs FLUX.1 Kontext dev), 6-panel comic page (needs Qwen3 32B), 20 long-form articles (needs Llama 3.3 70B), Full codebase review (needs Qwen2.5-Coder 14B), Character sheet, 12 poses (needs FLUX.1 dev), 100-photo restoration batch (needs FLUX.1 Kontext dev), 24-frame storyboard (needs Qwen3 32B), 100-photo restore and enlarge (needs FLUX.1 Kontext dev).
This card is $499 to buy. The cheapest listed rate on Vast.ai is $0.049/hour, but that is the floor: we budget $0.059/hour, a 20% premium, because idle time, storage and unavailable cheap instances all land on the same bill. At that rate buying wins after 8,486 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 | $43 | 11.6 years |
| 8 hours a day, working on it | 2,920 | $172 | 2.9 years |
| 24/7, always-on agent | 8,760 | $515 | 11.6 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.