Wan 2.1 I2V 14B 720P on 6 GB of VRAM
Not entirely. Even Q4_K_M is 12.1 GB over 6 GB, so ComfyUI keeps part of it in system RAM. The same image-to-video model trained for 1280×720. Identical file sizes to the 480P version, but 720p frames need far more working memory.
The smallest sensible file, Q4_K_M (11.3 GB), needs about 18.1 GB - 12.1 GB more than 6 GB GPU has. ComfyUI can still run it by streaming part of the model from system RAM. How much slower that is depends on your ComfyUI version, the file format and the PCIe link - see the note below.
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 →
Kijai's WanVideoWrapper (BlockSwap): even with all 40 blocks swapped to system RAM, the FP8 file would not fit on 6 GB. Use a GGUF file instead. estimate
01Other amounts of VRAM
02Every file, on 6 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 32.8 GB | 39.6 GB | 33.6 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · city96 | 18.1 GB | 24.9 GB | 18.9 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 16.4 GB | 23.2 GB | 17.2 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 14.2 GB | 21.0 GB | 15.0 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · city96 | 12.7 GB | 19.5 GB | 13.5 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M ← GGUF · city96 | 11.3 GB | 18.1 GB | 12.1 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · city96 | 8.6 GB | 15.4 GB | 9.4 GB too big | noticeable loss of detail | Hugging Face → |
“Needed” adds 6 GB of working memory for Wan 2.1 I2V 720P and a 0.8 GB reserve. Sizes 2026-10-01.
03What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | wan2.1-i2v-14b-720p-Q4_K_M.gguf Q4_K_M · city96/Wan2.1-I2V-14B-720P-gguf | models/unet | 11.3 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_2.1_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 | 19.6 GB | |||
Alternatives: UMT5-XXL FP16 (11.4 GB). Sizes from Hugging Face, 2026-10-01.
04The text encoder
Take the smallest UMT5-XXL + CLIP Vision H file (3.7 GB): it is the only one that fits in 6 GB on its own. Sizes: 16-bit 11.4 GB, FP8 6.7 GB, GGUF Q4_K_M 3.7 GB (plus CLIP Vision H (1.3 GB) for the input image). Why the encoder does not count against VRAM →