Wan Animate 2 (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 (14.2 GB). The July 2026 successor to Wan 2.2 Animate, adding text-driven camera and viewpoint control. The distilled variant runs in about 10 steps.
Q6_K (14.2 GB) fits with only 0.5 GB to spare (about 19.5 GB of 20 GB). Quality: very close to the original. For better quality, INT8 (16.7 GB) also runs, with about 2.0 GB spilling into system RAM - a little slower, still practical.
Also try the INT8 file (16.7 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 | Wan-Animate-2-14B-TURBO-Q6_K.gguf Q6_K · realrebelai/Wan-Animate-2_GGUFs | models/unet | 14.2 GB | Download → |
| Text encoder | umt5_xxl_fp8_e4m3fn_scaled.safetensors UMT5-XXL FP8 (scaled) · Comfy-Org/Wan-Animate-2 | models/text_encoders | 6.7 GB | Download → |
| VAE | Wan2_1_VAE_bf16.safetensors Wan 2.1 VAE BF16 (Kijai) · Comfy-Org/Wan-Animate-2 | models/vae | 0.3 GB | Download → |
| Also needed | clip_vision_h.safetensors CLIP Vision H · Comfy-Org/Wan-Animate-2 | models/clip_vision | 1.3 GB | Download → |
| Total download · keep about the same free on disk | 22.5 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 | 32.8 GB | 38.1 GB | 18.1 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · realrebelai | 18.1 GB | 23.4 GB | 3.4 GB too big | practically identical to the original | Hugging Face → |
| INT8 SAFETENSORS · Comfy-Org | 16.7 GB | 22.0 GB | spills 2.0 GB | practically identical to the original | Hugging Face → |
| Q6_K ← GGUF · realrebelai | 14.2 GB | 19.5 GB | fits · 0.5 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · realrebelai | 12.7 GB | 18.0 GB | fits · 2.0 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · realrebelai | 11.3 GB | 16.6 GB | fits · 3.4 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · realrebelai | 8.6 GB | 13.9 GB | fits · 6.1 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · realrebelai | 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 Animate 2 and a 0.8 GB reserve. Sizes 2026-10-01.