122 FPS average at 1440p across 9 games, anchored estimate · smooth 100+ FPS 1440p gaming across demanding AAA titles
122 Avg FPS Includes estimates
This card is still waiting on bench time. Until it gets there the figures are anchored estimates, interpolated from cards we measured on the same suite. Across our 9-game suite at 1440p, AMD Radeon RX 6900 XT averages 122 FPS. The ceiling is Counter-Strike 2 at 168 FPS; the floor is Alan Wake 2 at 80 FPS, a 2.1x 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 288W against the 300W rating.
| Benchmark | Result | 1% Low | VRAM Used | Power | Data |
|---|---|---|---|---|---|
| Cyberpunk 2077 1440p · Ultra | 93 FPS | 74 | 6.75 GB | 285 W | Estimated |
| Red Dead Redemption 2 1440p · Favor Quality | 103 FPS | 80 | 6.57 GB | 279 W | Estimated |
| Alan Wake 2 1440p · High | 80 FPS | 66 | 9.49 GB | 276 W | Estimated |
| Baldur's Gate 3 1440p · Ultra | 161 FPS | 132 | 7 GB | 288 W | Estimated |
| Black Desert Online 1440p · Remastered | 145 FPS | 93 | 5.29 GB | 285 W | Estimated |
| Counter-Strike 2 1440p · Very High | 168 FPS | 109 | 7.13 GB | 221 W | Estimated |
| Diablo 4 1440p · Ultra | 143 FPS | 109 | 9.84 GB | 282 W | Estimated |
| Escape from Tarkov 1440p · Ultra | 111 FPS | 93 | 14.72 GB | 237 W | Estimated |
| The Witcher 3 1440p · Ultra | 92 FPS | 77 | 7.05 GB | 285 W | Estimated |
| Architecture | RDNA 2 (Navi 21) |
| Stream processors | 5,120 |
| VRAM | 16GB GDDR6 |
| Memory bus | 256-bit |
| Memory bandwidth | 512 GB/s |
| Boost clock | 2,250 MHz |
| TDP | 300 W |
| Process | 7nm |
| Interface | PCIe 4.0 x16 |
| Release date | 2020-12-08 |
| Launch MSRP | $999 |
AMD Radeon RX 6900 XT averages 122 FPS at 1440p on our suite. This card is still waiting on bench time. Until it gets there the figures are anchored estimates, interpolated from cards we measured on the same suite.
100% = this card, Gaming headline metric (Avg FPS). #20 of 82 desktop cards in this vertical.
| GPU | Relative | % | Avg FPS |
|---|---|---|---|
| NVIDIA GeForce RTX 3080 Ti | 107% | 130 | |
| AMD Radeon RX 9070 GRE | 103% | 126 | |
| NVIDIA GeForce RTX 3080 12GB | 102% | 125 | |
| NVIDIA GeForce RTX 4070 Super | 102% | 125 | |
| AMD Radeon RX 6900 XT | 100% | 122 | |
| AMD Radeon RX 9070 | 99% | 121 | |
| AMD Radeon RX 7800 XT | 97% | 118 | |
| GeForce RTX 5070 | 92% | 112 | |
| NVIDIA GeForce RTX 4070 | 90% | 110 |
Same card, other workloads: AMD Radeon RX 6900 XT AI benchmarks, LLM tokens/sec, image generation & VRAM fit
| Transistors | 26,800 million |
| Die size | 520 mm² |
| Process node | 7 nm |
| Fabricated by | TSMC |
| Transistor density | 51.5 million per mm² |
Denser than 85% 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 | 21.8 min | n/a | estimate, 0 of 1 stage measured |
Can't run: 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).