Wan 2.1 VACE 14B on 16 GB of VRAM
Download Q3_K_S (7.8 GB). With the model's working memory it needs about 12.6 GB, leaving 3.4 GB spare on 16 GB. Quality: noticeable loss of detail. For better quality, Q4_K_M (11.6 GB) also runs, with about 0.4 GB spilling into system RAM — a little slower, still practical.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | Wan2.1_14B_VACE-Q3_K_S.gguf Q3_K_S · QuantStack/Wan2.1_14B_VACE-GGUF | models/unet | 7.8 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 → |
| Total download · keep about the same free on disk | 14.8 GB | |||
Alternatives: UMT5-XXL FP16 (11.4 GB). The 16-bit text encoder is a little more faithful; the smaller one is chosen here because it loads faster and needs less RAM. Sizes read from Hugging Face (2026-09-25). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.
System RAM: 32 GB or more. ComfyUI keeps the model file, the text encoder and the VAE in system RAM and moves them to the GPU as needed. With this set of files that is about 14.8 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 20.8 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated
02Every file, on 16 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 34.7 GB | 39.5 GB | 23.5 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · QuantStack | 18.7 GB | 23.5 GB | 7.5 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · QuantStack | 14.5 GB | 19.3 GB | 3.3 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · QuantStack | 13.0 GB | 17.8 GB | spills 1.8 GB | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · QuantStack | 11.6 GB | 16.4 GB | spills 0.4 GB | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_S ← GGUF · QuantStack | 7.8 GB | 12.6 GB | fits · 3.4 GB spare | noticeable loss of detail | Hugging Face → |
Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 4 GB working memory for this model + 0.8 GB kept free for the system.
03The text encoder
UMT5-XXL: 11.4 GB as 16-bit, 6.7 GB as FP8, 3.7 GB as GGUF Q4_K_M. ComfyUI encodes the prompt first and can push the encoder out of VRAM before sampling, so it does not have to fit together with the model. On 16 GB the FP8 encoder fits on its own, so prompt encoding stays fast.