Wan 2.2 A14B (T2V / I2V) is a video generation model by Alibaba (Wan) (14.3B per expert, two experts swapped in turn; text encoder: umT5-XXL). Two 14B experts (early and late steps) swapped in turn; the high-quality standard.
Change precision, resolution or length →
| Precision | Model size | 480p, 5 s | 720p, 5 s |
|---|---|---|---|
| BF16 / FP16 (uncompressed) | 28.6 GB | 33.1 GB all in VRAM 68.0 GB | 36.6 GB all in VRAM 71.5 GB |
| FP8 (half size, near-lossless) | 14.6 GB | 19.1 GB all in VRAM 40.0 GB | 22.6 GB all in VRAM 43.5 GB |
| GGUF Q8_0 (similar to FP8) | 15.3 GB | 19.8 GB all in VRAM 41.4 GB | 23.3 GB all in VRAM 44.9 GB |
| GGUF Q5_K_S | 10.2 GB | 14.7 GB all in VRAM 31.1 GB | 18.2 GB all in VRAM 34.6 GB |
| GGUF Q4_K_S (popular low-VRAM choice) | 8.6 GB | 13.1 GB all in VRAM 28.0 GB | 16.6 GB all in VRAM 31.5 GB |
| GGUF Q3_K_S (lower quality) | 6.7 GB | 11.2 GB all in VRAM 24.2 GB | 14.7 GB all in VRAM 27.8 GB |
Bold = VRAM needed when ComfyUI swaps the text encoder and the model. "All in VRAM" = keeping both loaded. Text encoder assumed at FP8. Official: 80 GB+ on a single GPU without offloading (measured with the official implementation).
| GPU | VRAM | Best precision | VRAM needed | Verdict | Buy |
|---|---|---|---|---|---|
| RTX 3060 12GB previous gen | 12 GB | GGUF Q3_K_S | 11.2 GB | ○ Runs with model swapping | Check price |
| Radeon RX 6700 XT previous gen | 12 GB | GGUF Q3_K_S | 11.2 GB | ○ Runs with model swapping | Check price |
| Intel Arc B580 | 12 GB | GGUF Q3_K_S | 11.2 GB | ○ Runs with model swapping | Check price |
| RTX 4070 Ti previous gen | 12 GB | GGUF Q3_K_S | 11.2 GB | ○ Runs with model swapping | Check price |
| RTX 4070 / SUPER previous gen | 12 GB | GGUF Q3_K_S | 11.2 GB | ○ Runs with model swapping | Check price |
| RTX 5070 | 12 GB | GGUF Q3_K_S | 11.2 GB | ○ Runs with model swapping | Check price |
| RTX 4060 Ti 16GB previous gen | 16 GB | GGUF Q5_K_S | 14.7 GB | ○ Runs with model swapping | Check price |
| Radeon RX 7600 XT previous gen | 16 GB | GGUF Q5_K_S | 14.7 GB | ○ Runs with model swapping | Check price |
| Radeon RX 9060 XT 16GB | 16 GB | GGUF Q5_K_S | 14.7 GB | ○ Runs with model swapping | Check price |
| RTX 5060 Ti 16GB | 16 GB | GGUF Q5_K_S | 14.7 GB | ○ Runs with model swapping | Check price |
| Radeon RX 6800 previous gen | 16 GB | GGUF Q5_K_S | 14.7 GB | ○ Runs with model swapping | Check price |
| Radeon RX 7800 XT previous gen | 16 GB | GGUF Q5_K_S | 14.7 GB | ○ Runs with model swapping | Check price |
| Radeon RX 9070 XT | 16 GB | GGUF Q5_K_S | 14.7 GB | ○ Runs with model swapping | Check price |
| Radeon RX 9070 | 16 GB | GGUF Q5_K_S | 14.7 GB | ○ Runs with model swapping | Check price |
| RTX 4070 Ti SUPER previous gen | 16 GB | GGUF Q5_K_S | 14.7 GB | ○ Runs with model swapping | Check price |
| RTX 4080 previous gen | 16 GB | GGUF Q5_K_S | 14.7 GB | ○ Runs with model swapping | Check price |
| RTX 4080 SUPER previous gen | 16 GB | GGUF Q5_K_S | 14.7 GB | ○ Runs with model swapping | Check price |
| RTX 5070 Ti | 16 GB | GGUF Q5_K_S | 14.7 GB | ○ Runs with model swapping | Check price |
| RTX 5080 | 16 GB | GGUF Q5_K_S | 14.7 GB | ○ Runs with model swapping | Check price |
| Radeon RX 7900 XT previous gen | 20 GB | FP8 | 19.1 GB | ○ Runs with model swapping | Check price |
| RTX 3090 previous gen | 24 GB | FP8 | 19.1 GB | ○ Runs with model swapping | Check price |
| Radeon RX 7900 XTX previous gen | 24 GB | FP8 | 19.1 GB | ○ Runs with model swapping | Check price |
| RTX 4090 previous gen | 24 GB | FP8 | 19.1 GB | ○ Runs with model swapping | Check price |
| RTX 5090 | 32 GB | FP8 | 19.1 GB | ○ Runs with model swapping | Check price |
ComfyUI also runs on AMD Radeon (ROCm) and Intel Arc, but setup is harder than on NVIDIA and some features (such as FP8 acceleration) are not supported.
→ Image & Video AI VRAM Calculator (all 15 models) / Local LLM VRAM Calculator
Estimates for ComfyUI, about ±20%. Model specs from the publisher's config files and released file sizes (checked October 2026).