Can the RTX 3090 24 GB run Wan 2.2 Animate 14B?
Yes, but only just: FP8 leaves 1.4 GB free on the RTX 3090 24 GB.
FP8 (17.3 GB) fits with only 1.4 GB to spare (about 22.6 GB of 24 GB).
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | Wan2_2-Animate-14B_fp8_scaled_e4m3fn_KJ_v2.safetensors FP8 · Kijai/WanVideo_comfy_fp8_scaled | models/diffusion_models | 17.3 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 | clip_vision_h.safetensors CLIP Vision H · Comfy-Org/Wan_2.1_ComfyUI_repackaged | models/clip_vision | 1.3 GB | Download → |
| Total download · keep about the same free on disk | 25.6 GB | |||
Alternatives: UMT5-XXL FP16 (11.4 GB). Sizes from Hugging Face, 2026-10-01.
02Every Wan 2.2 Animate file on 24 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 34.5 GB | 39.8 GB | 15.8 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · QuantStack | 18.7 GB | 24.0 GB | spills 0.0 GB | practically identical to the original | Hugging Face → |
| FP8 ← SAFETENSORS · Kijai | 17.3 GB | 22.6 GB | fits · 1.4 GB spare | practically identical to the original | Hugging Face → |
| INT8 SAFETENSORS · Comfy-Org | 18.4 GB | 23.7 GB | fits · 0.3 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · QuantStack | 14.6 GB | 19.9 GB | fits · 4.1 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · QuantStack | 13.0 GB | 18.3 GB | fits · 5.7 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · QuantStack | 11.5 GB | 16.8 GB | fits · 7.2 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · QuantStack | 8.6 GB | 13.9 GB | fits · 10.1 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · QuantStack | 6.5 GB | 11.8 GB | fits · 12.2 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 4.5 GB of working memory for Wan 2.2 Animate 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 Animate on a RTX 3090 24 GB, send your time per image and peak VRAM and it will appear here, credited.
04About the RTX 3090 24 GB
The RTX 3090 24 GB (Ampere) has no FP8 compute. FP8 files still load and save memory, but ComfyUI converts them back before the maths, so there is no speed gain - Q8_0 GGUF is the closer-to-original 8-bit choice. ComfyUI can compute INT8 files natively on NVIDIA, which is worth a try where a model offers one.
24 GB GDDR6X · 384-bit · 936 GB/s · Ampere. Everything that runs on it →
05Questions
How much VRAM does Wan 2.2 Animate need?
Around 11.8 GB with the smallest file (Q2_K) and 22.6 GB with an 8-bit file (FP8). The full 16-bit file needs about 39.8 GB.
Which Wan 2.2 Animate file should I download for the RTX 3090 24 GB?
FP8 (17.3 GB) from Kijai/WanVideo_comfy_fp8_scaled.
FP8 or Q8_0 for Wan 2.2 Animate on the RTX 3090 24 GB?
Q8_0 (18.7 GB). The RTX 3090 24 GB has no FP8 maths, so FP8 (17.3 GB) only saves memory and is a step further from the original.
How much do I need to download for Wan 2.2 Animate on the RTX 3090 24 GB?
25.6 GB: Wan2_2-Animate-14B_fp8_scaled_e4m3fn_KJ_v2.safetensors, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, clip_vision_h.safetensors.