Text or image to video on a single consumer GPU. Made by Alibaba.
Use ComfyUI
Wan 2.2 5B is a video generation model from Alibaba. Text or image to video on a single consumer GPU. Running it locally needs about 16 GB of memory.
The least memory you need, by Apple chip:
Runs well on: RTX 3090, RTX 4090, RTX 5090, Radeon RX 7900 XTX. Runs slowly with help from system RAM on: RTX 4060 Ti 16GB, RTX 4070 Ti Super, RTX 4080 / 4080 Super, RTX 5060 Ti 16GB, RTX 5070 Ti, RTX 5080, Radeon RX 7800 XT, Radeon RX 9070 XT.
As an Amazon Associate I earn from qualifying purchases.
About 16 GB of video memory or unified memory. On a Mac, the smallest configuration that runs it is 24 GB.
A 16 GB M4 Mac runs it slow, about about 27 min per 4 second clip. An 8 GB M1 Mac cannot run it.
Yes, the model is free to download. Its licence is listed as Apache 2.0. That is a permissive licence that allows commercial use.
Use ComfyUI.
| Machine | Verdict | Speed |
|---|---|---|
| M1 8GB | Too big | |
| M4 16GB | Slow | about 27 min |
| M4 32GB | Runs well | about 13 min |
| M4 Pro 48GB | Runs great | about 7 min |
| M4 Max 128GB | Runs great | about 4 min |
| M3 Ultra 512GB | Runs great | about 4 min |
| RTX 4060 | Too big | |
| RTX 4070/4070 Super | Too big | |
| RTX 5070 Ti | Slow | about 8 min |
| RTX 3090 | Runs great | about 7 min |
| RTX 5090 | Runs great | about 2 min |
| Ryzen AI Max+ 395 128GB | Runs great | about 7 min |
| CPU only 32GB | Too big |