Wan 2.2 TI2V 5B on 16 GB of VRAM
Yes, but only just: 16-bit leaves 2.2 GB free on 16 GB. A single dense 5B model for text- or image-to-video at 720p. The friendliest Wan for 8–12 GB cards.
Runs well
Yes.
Take 16-bit (10.0 GB). In use it comes to about 13.8 GB, with 2.2 GB left over on 16 GB.
Best file16-bit
File size10.0 GB
VRAM needed~13.8 GB
System RAM32 GB+
Memory map · 16 GB GPU13.8 GB / 16 GB
08 GB16 GB
Weights 16-bit · 10.0 GBWorking memory · 3.0 GBReserve · 0.8 GBFree · 2.2 GB
calculated How this is counted.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | wan2.2_ti2v_5B_fp16.safetensors 16-bit · Comfy-Org/Wan_2.2_ComfyUI_Repackaged | models/diffusion_models | 10.0 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 | wan2.2_vae.safetensors Wan 2.2 VAE · Comfy-Org/Wan_2.2_ComfyUI_Repackaged | models/vae | 1.4 GB | Download → |
| Total download · keep about the same free on disk | 18.1 GB | |||
Alternatives: UMT5-XXL FP16 (11.4 GB). Sizes from Hugging Face, 2026-10-01.
Free ComfyUI workflow, tested on my RTX 5060 Ti: text to video workflow (.json). Drag the file into ComfyUI. All workflows →
02Every file, on 16 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · Comfy-Org | 10.0 GB | 13.8 GB | fits · 2.2 GB spare | the original weights | Hugging Face → |
| Q8_0 GGUF · QuantStack | 5.4 GB | 9.2 GB | fits · 6.8 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · QuantStack | 4.2 GB | 8.0 GB | fits · 8.0 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · QuantStack | 3.8 GB | 7.6 GB | fits · 8.4 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · QuantStack | 3.4 GB | 7.2 GB | fits · 8.8 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · QuantStack | 2.5 GB | 6.3 GB | fits · 9.7 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · QuantStack | 1.9 GB | 5.7 GB | fits · 10.3 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 3 GB of working memory for Wan 2.2 5B and a 0.8 GB reserve. Sizes 2026-10-01.