Can the RTX 5090 32 GB run Wan 2.2 S2V 14B?
Yes. FP8 fits on the RTX 5090 32 GB with 10.8 GB to spare.
FP8 (16.4 GB) needs about 21.2 GB in use, so 10.8 GB of the 32 GB stays free: room for a larger image, a LoRA or a ControlNet.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | wan2.2_s2v_14B_fp8_scaled.safetensors FP8 · Comfy-Org/Wan_2.2_ComfyUI_Repackaged | models/diffusion_models | 16.4 GB | Download → |
| Text encoder | umt5_xxl_fp8_e4m3fn_scaled.safetensors UMT5-XXL FP8 (scaled) · Comfy-Org/Wan_2.1_ComfyUI_repackaged | models/text_encoders | 6.7 GB | Download → |
| VAE | wan_2.1_vae.safetensors Wan 2.1 VAE · Comfy-Org/Wan_2.2_ComfyUI_Repackaged | models/vae | 0.3 GB | Download → |
| Also needed | wav2vec2_large_english_fp16.safetensors wav2vec2 large English FP16 (audio encoder) · Comfy-Org/Wan_2.2_ComfyUI_Repackaged | models/audio_encoders | 0.6 GB | Download → |
| Total download · keep about the same free on disk | 24.0 GB | |||
Alternatives: UMT5-XXL FP16 (11.4 GB). Sizes from Hugging Face, 2026-10-01.
02Every Wan 2.2 S2V file on 32 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 32.6 GB | 37.4 GB | 5.4 GB too big | the original weights | Hugging Face → |
| FP8 ← SAFETENSORS · Comfy-Org | 16.4 GB | 21.2 GB | fits · 10.8 GB spare | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · QuantStack | 19.6 GB | 24.4 GB | fits · 7.6 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · QuantStack | 16.2 GB | 21.0 GB | fits · 11.0 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · QuantStack | 15.0 GB | 19.8 GB | fits · 12.2 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · QuantStack | 13.9 GB | 18.7 GB | fits · 13.3 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · QuantStack | 11.4 GB | 16.2 GB | fits · 15.8 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · QuantStack | 9.5 GB | 14.3 GB | fits · 17.7 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 4 GB of working memory for Wan 2.2 S2V and a 0.8 GB reserve. Sizes 2026-10-01.
03Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run Wan 2.2 S2V on a RTX 5090 32 GB, send your time per image and peak VRAM and it will appear here, credited.
04About the RTX 5090 32 GB
The RTX 5090 32 GB is a Blackwell GPU with FP8 and FP4 hardware: ComfyUI computes Comfy-Org's FP8 files natively here, and NVFP4 files (where a model offers them) are faster still.
32 GB GDDR7 · 512-bit · 1792 GB/s · Blackwell. Everything that runs on it →
05Questions
How much VRAM does Wan 2.2 S2V need?
Around 14.3 GB with the smallest file (Q2_K) and 21.2 GB with an 8-bit file (FP8). The full 16-bit file needs about 37.4 GB.
Which Wan 2.2 S2V file should I download for the RTX 5090 32 GB?
FP8 (16.4 GB) from Comfy-Org/Wan_2.2_ComfyUI_Repackaged.
FP8 or Q8_0 for Wan 2.2 S2V on the RTX 5090 32 GB?
FP8 (16.4 GB): the RTX 5090 32 GB computes it natively, while Q8_0 (19.6 GB) is unpacked on the fly.
How much do I need to download for Wan 2.2 S2V on the RTX 5090 32 GB?
24.0 GB: wan2.2_s2v_14B_fp8_scaled.safetensors, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, wav2vec2_large_english_fp16.safetensors.