Wan 2.2 Animate 14B on 20 GB of VRAM
Not at full quality. The 16-bit and 8-bit files are too big for 20 GB; the largest that fits is Q6_K (14.6 GB). Character animation and replacement: a reference image of a person is driven by the motion and face of another video.
Runs
Yes, with a compressed file.
Q6_K (14.6 GB) fits with only 0.1 GB to spare (about 19.9 GB of 20 GB). Quality: very close to the original.
Best fileQ6_K
File size14.6 GB
VRAM needed~19.9 GB
System RAM32 GB+
Memory map · 20 GB GPU19.9 GB / 20 GB
010 GB20 GB
Weights Q6_K · 14.6 GBWorking memory · 4.5 GBReserve · 0.8 GBFree · 0.1 GB
calculated How this is counted.
Also try the FP8 file (17.3 GB) on NVIDIA GPUs. It does not fit entirely, but a current ComfyUI streams the overflow from RAM and native 8-bit files often beat a small GGUF that does fit. Dynamic VRAM →
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | Wan2.2-Animate-14B-Q6_K.gguf Q6_K · QuantStack/Wan2.2-Animate-14B-GGUF | models/unet | 14.6 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 | 22.9 GB | |||
Alternatives: UMT5-XXL FP16 (11.4 GB). Sizes from Hugging Face, 2026-10-01.
02Every file, on 20 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 34.5 GB | 39.8 GB | 19.8 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · QuantStack | 18.7 GB | 24.0 GB | 4.0 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Kijai | 17.3 GB | 22.6 GB | 2.6 GB too big | practically identical to the original | Hugging Face → |
| INT8 SAFETENSORS · Comfy-Org | 18.4 GB | 23.7 GB | 3.7 GB too big | practically identical to the original | Hugging Face → |
| Q6_K ← GGUF · QuantStack | 14.6 GB | 19.9 GB | fits · 0.1 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · QuantStack | 13.0 GB | 18.3 GB | fits · 1.7 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · QuantStack | 11.5 GB | 16.8 GB | fits · 3.2 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · QuantStack | 8.6 GB | 13.9 GB | fits · 6.1 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · QuantStack | 6.5 GB | 11.8 GB | fits · 8.2 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.