Home / GPU guide / RTX 2080 Ti 22GB (modded)
| Size (16:9) | 5s | 8s | 10s | 15s |
|---|---|---|---|---|
| 416 × 256 0.1MP · flicker-prone | 2 min 5 s VRAM 17G | 2 min 20 s VRAM 17G | 2 min 31 s VRAM 18G | 2 min 60 s VRAM 18G |
| 864 × 480 0.4MP | 3 min 26 s VRAM 19G | 4 min 48 s VRAM 20G | 6 min 1 s VRAM 20G | 9 min 57 s VRAM 21G |
| 960 × 544 0.5MP | 3 min 60 s VRAM 19G | 6 min 5 s VRAM 21G | 7 min 54 s VRAM 21G | 13 min 56 s VRAM 21G |
| 1152 × 640 0.7MP | 5 min 21 s VRAM 20G | 9 min 16 s VRAM 21G | 12 min 43 s VRAM 21G | 24 min 50 s VRAM 21G |
| 1376 × 768 1.0MP · above native | 8 min 6 s VRAM 21G | 15 min 48 s VRAM 21G | 22 min 59 s VRAM 21G | 49 min 46 s VRAM 21G |
| 1920 × 1088 2.0MP · above native | 23 min 1 s VRAM 21G | 56 min 17 s VRAM 21G | ✕ 1.5 h VRAM 21G | ✕ 3.9 h VRAM 21G |
Times are per whole clip (model load and text encoding included); the first run is slower due to kernel compilation. ⚠ = weight offloading / noticeably slower; ✕ = not recommended.
--fast-disk768p 5s; 4-8 steps; 1-5 min per clip
Yes. Estimated with 32GB RAM + fast-disk: 1920×1088·8s at ~56 min 17 s per clip. Configs that exceed VRAM fall back to weight offloading (slower, but they still render).
About 56 min 17 s per 1920×1088·8s clip (including model load and encoding). Longer or denser clips scale quadratically in the attention term.
At least 64GB of system RAM recommended (minimum 32GB plus a 16GB pagefile). With 32GB, always enable --fast-disk or weights spill into the pagefile.
Stack step distillation (e.g. LightX2V Turbo 4-step v1.1 768p), enable SageAttention / Kitchen attention; for long clips try SLA / VSA sparse attention. All of it is switchable in step 2 of the calculator.
→ Run the numbers for your RAM and budget in the calculator (RTX 2080 Ti 22GB (modded) pre-filled)
Same tier: GTX 1050 Ti 4GB · GTX 1060 6GB · GTX 1070 8GB · GTX 1080 8GB · GTX 1080 Ti 11GB · RTX 2060 6GB · RTX 2060 12GB · RTX 2060 Super 8GB
Related: Hardware guide · Acceleration compared · 8GB VRAM setups