Home / GPU guide / RTX 4090 48GB (modded)
| Size (16:9) | 5s | 8s | 10s | 15s |
|---|---|---|---|---|
| 416 × 256 0.1MP · flicker-prone | 1 min 3 s VRAM 44G | 1 min 12 s VRAM 45G | 1 min 18 s VRAM 45G | 1 min 36 s VRAM 45G |
| 864 × 480 0.4MP | 1 min 53 s VRAM 46G | 2 min 43 s VRAM 26G | 3 min 28 s VRAM 27G | 5 min 51 s VRAM 29G |
| 960 × 544 0.5MP | 2 min 13 s VRAM 46G | 3 min 30 s VRAM 27G | 4 min 36 s VRAM 28G | 8 min 18 s VRAM 30G |
| 1152 × 640 0.7MP | 3 min 3 s VRAM 26G | 5 min 27 s VRAM 29G | 7 min 33 s VRAM 30G | 15 min 1 s VRAM 33G |
| 1376 × 768 1.0MP · above native | 4 min 44 s VRAM 28G | 9 min 27 s VRAM 31G | 13 min 52 s VRAM 33G | 30 min 26 s VRAM 38G |
| 1920 × 1088 2.0MP · above native | 13 min 53 s VRAM 33G | 34 min 29 s VRAM 39G | 55 min 50 s VRAM 39G | ✕ 2.4 h VRAM 39G |
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-disk1344x768 full length 5-15s; 4-8 steps; ~80s end-to-end for a 3s clip (measured on our 5090)
Yes. Estimated with 32GB RAM + fast-disk: 1920×1088·10s at ~55 min 50 s per clip. Configs that exceed VRAM fall back to weight offloading (slower, but they still render).
About 55 min 50 s per 1920×1088·10s clip (including model load and encoding). Longer or denser clips scale quadratically in the attention term.
At least 64GB of system RAM recommended (minimum 48GB plus a 16GB pagefile). With 32GB, always enable --fast-disk or weights spill into the pagefile.
Stack step distillation (e.g. LightX2V Turbo 8-step v1.0), 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 4090 48GB (modded) pre-filled)
Same tier: RTX 3090 24GB · RTX 4070 Ti Super 16GB · RTX 4080 16GB · RTX 4080 32GB (modded) · RTX 4080 Super 16GB · RTX 4080 Super 32GB (modded) · RTX 4090 24GB · RTX 4090 D 24GB
Related: Hardware guide · Acceleration compared · 8GB VRAM setups