9 games at 1440p, 74 FPS on average, anchored estimate · solid 60+ FPS 1440p gaming, with headroom in lighter titles
74 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 2070 SUPER averages 74 FPS. The ceiling is Counter-Strike 2 at 124 FPS; the floor is Alan Wake 2 at 46 FPS, a 2.7x 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 206W against the 215W rating.
| Benchmark | Result | 1% Low | VRAM Used | Power | Data |
|---|---|---|---|---|---|
| Cyberpunk 2077 1440p · Ultra | 55 FPS | 44 | 6.75 GB | 204 W | Estimated |
| Red Dead Redemption 2 1440p · Favor Quality | 63 FPS | 49 | 6.57 GB | 200 W | Estimated |
| Alan Wake 2 1440p · High | 46 FPS | 38 | 7.36 GB | 198 W | Estimated |
| Baldur's Gate 3 1440p · Ultra | 89 FPS | 73 | 7 GB | 206 W | Estimated |
| Black Desert Online 1440p · Remastered | 94 FPS | 60 | 5.29 GB | 204 W | Estimated |
| Counter-Strike 2 1440p · Very High | 124 FPS | 67 | 7.13 GB | 172 W | Estimated |
| Diablo 4 1440p · Ultra | 77 FPS | 59 | 7.36 GB | 202 W | Estimated |
| Escape from Tarkov 1440p · Ultra | 66 FPS | 49 | 7.36 GB | 185 W | Estimated |
| The Witcher 3 1440p · Ultra | 51 FPS | 43 | 7.05 GB | 204 W | Estimated |
| Architecture | Turing |
| CUDA cores | 2,560 |
| VRAM | 8GB GDDR6 |
| Memory bus | 256-bit |
| Memory bandwidth | 448 GB/s |
| Boost clock | 1,770 MHz |
| TDP | 215 W |
| Process | 12nm |
| Interface | PCIe 3.0 x16 |
| Release date | 2019-07-09 |
| Launch MSRP | $499 |
NVIDIA GeForce RTX 2070 SUPER averages 74 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). #40 of 82 desktop cards in this vertical.
| GPU | Relative | % | Avg FPS |
|---|---|---|---|
| NVIDIA GeForce RTX 2080 Founders Edition | 108% | 80 | |
| AMD Radeon RX 9060 | 105% | 78 | |
| AMD Radeon RX 9060 XT | 104% | 77 | |
| NVIDIA TITAN V | 103% | 76 | |
| NVIDIA GeForce RTX 2070 SUPER | 100% | 74 | |
| AMD Radeon RX 6750 XT | 99% | 73 | |
| GeForce RTX 4060 | 97% | 72 | |
| Intel Arc B580 | 96% | 71 | |
| AMD Radeon RX 6700 XT | 95% | 70 |
Same card, other workloads: NVIDIA GeForce RTX 2070 SUPER AI benchmarks, LLM tokens/sec, image generation & VRAM fit
| Transistors | 13,600 million |
| Die size | 545 mm² |
| Fabricated by | TSMC |
| Transistor density | 25 million per mm² |
Denser than 30% 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).