9 games at 1440p, 85 FPS on average, anchored estimate · solid 60+ FPS 1440p gaming, with headroom in lighter titles
85 Avg FPS Includes estimates
These figures are anchored estimates, interpolated against the cards we measured first-party on the same suite, and they stay labeled as estimates until this card runs. Across our 9-game suite at 1440p, NVIDIA GeForce RTX 2080 Super averages 85 FPS. The ceiling is Counter-Strike 2 at 143 FPS; the floor is Alan Wake 2 at 53 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 240W against the 250W rating.
| Benchmark | Result | 1% Low | VRAM Used | Power | Data |
|---|---|---|---|---|---|
| Cyberpunk 2077 1440p · Ultra | 64 FPS | 51 | 6.75 GB | 238 W | Estimated |
| Red Dead Redemption 2 1440p · Favor Quality | 72 FPS | 56 | 6.57 GB | 232 W | Estimated |
| Alan Wake 2 1440p · High | 53 FPS | 44 | 7.36 GB | 230 W | Estimated |
| Baldur's Gate 3 1440p · Ultra | 103 FPS | 84 | 7 GB | 240 W | Estimated |
| Black Desert Online 1440p · Remastered | 108 FPS | 69 | 5.29 GB | 238 W | Estimated |
| Counter-Strike 2 1440p · Very High | 143 FPS | 77 | 7.13 GB | 200 W | Estimated |
| Diablo 4 1440p · Ultra | 89 FPS | 68 | 7.36 GB | 235 W | Estimated |
| Escape from Tarkov 1440p · Ultra | 76 FPS | 56 | 7.36 GB | 215 W | Estimated |
| The Witcher 3 1440p · Ultra | 58 FPS | 49 | 7.05 GB | 238 W | Estimated |
| Architecture | Turing (TU104) |
| CUDA cores | 3,072 |
| VRAM | 8GB GDDR6 |
| Memory bus | 256-bit |
| Memory bandwidth | 496 GB/s |
| Boost clock | 1,815 MHz |
| TDP | 250 W |
| Process | 12nm |
| Interface | PCIe 3.0 x16 |
| Release date | 2019-07-23 |
| Launch MSRP | $699 |
NVIDIA GeForce RTX 2080 Super averages 85 FPS at 1440p on our suite. These figures are anchored estimates, interpolated against the cards we measured first-party on the same suite, and they stay labeled as estimates until this card runs.
100% = this card, Gaming headline metric (Avg FPS). #32 of 82 desktop cards in this vertical.
| GPU | Relative | % | Avg FPS |
|---|---|---|---|
| NVIDIA GeForce RTX 3080 | 118% | 100 | |
| AMD Radeon RX 6800 XT | 116% | 99 | |
| AMD Radeon RX 7700 XT | 111% | 94 | |
| AMD Radeon RX 6800 | 105% | 89 | |
| NVIDIA GeForce RTX 2080 Super | 100% | 85 | |
| GeForce RTX 5060 Ti | 99% | 84 | |
| NVIDIA GeForce RTX 4060 Ti | 98% | 83 | |
| NVIDIA GeForce RTX 3070 Founders Edition | 96% | 82 | |
| NVIDIA GeForce RTX 2080 Founders Edition | 94% | 80 |
Same card, other workloads: NVIDIA GeForce RTX 2080 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).