Wan 2.1 I2V 14B 480P on 12 GB of VRAM
Not entirely. Even Q3_K_M is 0.9 GB over 12 GB, so ComfyUI keeps part of it in system RAM. The image-to-video Wan 2.1, trained for 832×480. It has extra image-conditioning layers, so its files are bigger than the text-to-video 14B.
Nothing fits entirely, but Q3_K_M (8.6 GB) overflows by only about 0.9 GB. ComfyUI keeps that part in system RAM automatically: slower than a full fit, but usable.
Also try the FP8 file (16.4 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 →
Using Kijai's WanVideoWrapper instead of the native nodes? Its WanVideo BlockSwap node keeps part of the model in system RAM. To run the FP8 file (16.4 GB) on 12 GB, start with blocks_to_swap ≈ 23 (of 40). Each block is about 0.4 GB; raise the number if you still run out of memory, lower it for speed. estimate WanVideoWrapper →
01Other amounts of VRAM
02Every file, on 12 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 32.8 GB | 37.1 GB | 25.1 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · city96 | 18.1 GB | 22.4 GB | 10.4 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 16.4 GB | 20.7 GB | 8.7 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 14.2 GB | 18.5 GB | 6.5 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · city96 | 12.7 GB | 17.0 GB | 5.0 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · city96 | 11.3 GB | 15.6 GB | 3.6 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M ← GGUF · city96 | 8.6 GB | 12.9 GB | spills 0.9 GB | noticeable loss of detail | Hugging Face → |
“Needed” adds 3.5 GB of working memory for Wan 2.1 I2V 480P and a 0.8 GB reserve. Sizes 2026-10-01.
03What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | wan2.1-i2v-14b-480p-Q3_K_M.gguf Q3_K_M · city96/Wan2.1-I2V-14B-480P-gguf | models/unet | 8.6 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_2.1_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 | 16.8 GB | |||
Alternatives: UMT5-XXL FP16 (11.4 GB). Sizes from Hugging Face, 2026-10-01.