| File | wan2.1_t2v_14B_fp16.safetensors |
| Model | Wan 2.1 T2V 14B (video model, 14B) |
| Precision | 16-bit |
| Size | 28.6 GB |
| VRAM to fit | about 32.9 GB |
| Folder | ComfyUI/models/diffusion_models/ |
| Loader node | Load Diffusion Model (UNETLoader) |
| Source | Comfy-Org/Wan_2.1_ComfyUI_repackaged on Hugging Face |
Download wan2.1_t2v_14B_fp16.safetensors (28.6 GB)
Where to put it
Put the file in ComfyUI/models/diffusion_models/ (portable version: ComfyUI_windows_portable/ComfyUI/models/diffusion_models/). Older guides say models/unet: that folder still works. Press R in ComfyUI or restart it, then pick the file in Load Diffusion Model (UNETLoader).
If a workflow says “Value not in list” for that node, the workflow expects a file with another name. Click the node and choose this one.
Which graphics cards it fits
| VRAM | This file | Best file for that card (RTX 40/50) | |
|---|---|---|---|
| 6 GB | Not practical | Short by 26.9 GB | wan2.1-t2v-14b-Q4_K_M.gguf (10.1 GB) |
| 8 GB | Not practical | Short by 24.9 GB | wan2.1-t2v-14b-Q4_K_M.gguf (10.1 GB) |
| 10 GB | Not practical | Short by 22.9 GB | wan2.1-t2v-14b-Q3_K_M.gguf (7.6 GB) |
| 12 GB | Not practical | Short by 20.9 GB | wan2.1-t2v-14b-Q3_K_M.gguf (7.6 GB) |
| 16 GB | Offload only | Short by 16.9 GB: runs with part of it in system RAM, slower | wan2.1-t2v-14b-Q5_K_M.gguf (11.3 GB) |
| 20 GB | Offload only | Short by 12.9 GB: runs with part of it in system RAM, slower | wan2.1_t2v_14B_fp8_e4m3fn.safetensors (14.3 GB) |
| 24 GB | Offload only | Short by 8.9 GB: runs with part of it in system RAM, slower | wan2.1_t2v_14B_fp8_e4m3fn.safetensors (14.3 GB) |
| 32 GB | Offload only | Short by 0.9 GB: runs with part of it in system RAM, slower | wan2.1_t2v_14B_fp8_e4m3fn.safetensors (14.3 GB) |
| 48 GB | Runs well | Fits in VRAM, 15.1 GB to spare | this file |
Need = file × 1 + 3.5 GB for the picture and 0.8 GB for Windows and the browser — the same rule as the rest of the site.
What else you need
This file alone does not make a picture. With it you load:
| Role | File | Size | Folder |
|---|---|---|---|
| Model | wan2.1_t2v_14B_fp16.safetensors | 28.6 GB | models/diffusion_models |
| Text encoder | umt5_xxl_fp8_e4m3fn_scaled.safetensors | 6.7 GB | models/text_encoders |
| VAE | wan_2.1_vae.safetensors | 0.3 GB | models/vae |
35.6 GB in total. Smaller text-encoder versions and other options are on the Wan 2.1 14B page.
Other files of Wan 2.1 14B
| File | Precision | Size | VRAM to fit |
|---|---|---|---|
| wan2.1_t2v_14B_fp16.safetensors | 16-bit | 28.6 GB | 32.9 GB |
| wan2.1-t2v-14b-Q8_0.gguf | Q8_0 | 15.9 GB | 20.2 GB |
| wan2.1_t2v_14B_fp8_e4m3fn.safetensors | FP8 | 14.3 GB | 18.6 GB |
| wan2.1-t2v-14b-Q6_K.gguf | Q6_K | 12.5 GB | 16.8 GB |
| wan2.1-t2v-14b-Q5_K_M.gguf | Q5_K_M | 11.3 GB | 15.6 GB |
| wan2.1-t2v-14b-Q4_K_M.gguf | Q4_K_M | 10.1 GB | 14.4 GB |
| wan2.1-t2v-14b-Q3_K_M.gguf | Q3_K_M | 7.6 GB | 11.9 GB |
Same model, different compression. 8-bit files (FP8, INT8, Q8_0) look almost the same as 16-bit; below Q5 the loss starts to show.
Want the answer for your exact card? Check your GPU. Every file of every model: ComfyUI model files.
Size and source read from Hugging Face (2026-10-01).