| File | wan2.2_ti2v_5B_fp16.safetensors |
| Model | Wan 2.2 TI2V 5B (video model, 5B) |
| Precision | 16-bit |
| Size | 10.0 GB |
| VRAM to fit | about 13.8 GB |
| Folder | ComfyUI/models/diffusion_models/ |
| Loader node | Load Diffusion Model (UNETLoader) |
| Source | Comfy-Org/Wan_2.2_ComfyUI_Repackaged on Hugging Face |
Download wan2.2_ti2v_5B_fp16.safetensors (10.0 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 | Offload only | Short by 7.8 GB: runs with part of it in system RAM, slower | Wan2.2-TI2V-5B-Q2_K.gguf (1.9 GB) |
| 8 GB | Offload only | Short by 5.8 GB: runs with part of it in system RAM, slower | Wan2.2-TI2V-5B-Q5_K_M.gguf (3.8 GB) |
| 10 GB | Offload only | Short by 3.8 GB: runs with part of it in system RAM, slower | Wan2.2-TI2V-5B-Q8_0.gguf (5.4 GB) |
| 12 GB | Offload only | Short by 1.8 GB: runs with part of it in system RAM, slower | Wan2.2-TI2V-5B-Q8_0.gguf (5.4 GB) |
| 16 GB | Runs well | Fits in VRAM, 2.2 GB to spare | this file |
| 20 GB | Runs well | Fits in VRAM, 6.2 GB to spare | this file |
| 24 GB | Runs well | Fits in VRAM, 10.2 GB to spare | this file |
| 32 GB | Runs well | Fits in VRAM, 18.2 GB to spare | this file |
| 48 GB | Runs well | Fits in VRAM, 34.2 GB to spare | this file |
Need = file × 1 + 3 GB for the picture and 0.8 GB for Windows and the browser — the same rule as the rest of the site.
Measured with this exact file
| GPU | Time | Size | Steps | Peak VRAM | Source |
|---|---|---|---|---|---|
| RTX 5060 Ti 16 GB | 515 s per video (121 frames) | 1280x704 | 20 | 11.0 GB | measured by me, 2026-09-27 |
Time = sampling + VAE decode, after a warm-up run. Peak VRAM = memory in use on the whole card. How I measure.
What else you need
This file alone does not make a picture. With it you load:
| Role | File | Size | Folder |
|---|---|---|---|
| Model | wan2.2_ti2v_5B_fp16.safetensors | 10.0 GB | models/diffusion_models |
| Text encoder | umt5_xxl_fp8_e4m3fn_scaled.safetensors | 6.7 GB | models/text_encoders |
| VAE | wan2.2_vae.safetensors | 1.4 GB | models/vae |
18.1 GB in total. Smaller text-encoder versions and other options are on the Wan 2.2 5B page.
Other files of Wan 2.2 5B
| File | Precision | Size | VRAM to fit |
|---|---|---|---|
| wan2.2_ti2v_5B_fp16.safetensors | 16-bit | 10.0 GB | 13.8 GB |
| Wan2.2-TI2V-5B-Q8_0.gguf | Q8_0 | 5.4 GB | 9.2 GB |
| Wan2.2-TI2V-5B-Q6_K.gguf | Q6_K | 4.2 GB | 8.0 GB |
| Wan2.2-TI2V-5B-Q5_K_M.gguf | Q5_K_M | 3.8 GB | 7.6 GB |
| Wan2.2-TI2V-5B-Q4_K_M.gguf | Q4_K_M | 3.4 GB | 7.2 GB |
| Wan2.2-TI2V-5B-Q3_K_M.gguf | Q3_K_M | 2.5 GB | 6.3 GB |
| Wan2.2-TI2V-5B-Q2_K.gguf | Q2_K | 1.9 GB | 5.7 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.
Free workflow with this file
- Wan 2.2 TI2V 5B — text to video — 9 min for a 121-frame 1280×704 clip
Drag the .json into ComfyUI. All free workflows →
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).