Alibaba (Wan team) · 5B parameters · Apache 2.0
What GPU do you need to run Wan 2.2 5B?Memory and cards.
Wan 2.2 5B needs about 8 GB of GPU memory (VRAM) at its smallest (ComfyUI, with offloading, small videos), so a 16 GB card such as an RTX 4080 runs it. The cheapest card on our list that fits, an RTX 4060 Ti 16GB, costs about $0.14 an hour. At its largest (720p, the maker's own script) it needs about 24 GB.
GPU memory
Wan 2.2 5B, by version.
Resolution and video length add the most memory. How we work it out
| Version | Memory needed | Card size | Cards that fit | From |
|---|---|---|---|---|
| ComfyUI, with offloading, small videos | about 8 GB | 16–20 GB | RTX 4090, RTX 5090, RTX 3090, RTX 4080, RTX 3090 Ti, RTX 5080, RTX 5070 Ti, RTX 4070 Ti SUPER, RTX 5060 Ti 16GB, RTX 4060 Ti 16GB | $0.14/hr on an RTX 4060 Ti 16GB |
| 720p, the maker's own script | about 24 GB | 24 GB | RTX 4090, RTX 5090, RTX 3090, RTX 3090 Ti | $0.155/hr on an RTX 3090 |
Makes 720p video at 24 frames a second, from text or from a starting picture. ComfyUI's guide says it should fit in 8 GB with ComfyUI moving parts out to the computer's memory, at a small default size. Its maker says its own script needs a 24 GB card, such as an RTX 4090, for 720p. Apache 2.0, so commercial use is fine.
Run it
Start Wan 2.2 5B in minutes.
The rented machine downloads it straight from Hugging Face, not through your computer. On KernelMachine, Rent an Image maker with these files, below (ComfyUI makes videos too): they load into ComfyUI's model folders by themselves once it's ready. Already renting one? Pick it under Load from link on the rental's page, or run km load with each link. ComfyUI on a rented GPU
$ km load https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_ti2v_5B_fp16.safetensors
$ km load https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors
$ km load https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan2.2_vae.safetensors
Files to load
Wan 2.2 5B in ComfyUI.
The files ComfyUI's own "Wan 2.2 5B Video Generation" template uses, 18.1 GB in all. Each goes in its own folder, and Load from link puts it there. Then open that template from ComfyUI's template menu.
| File | Folder | Size |
|---|---|---|
| wan2.2_ti2v_5B_fp16.safetensors | models/diffusion_models | 10.0 GB |
| umt5_xxl_fp8_e4m3fn_scaled.safetensors | models/text_encoders | 6.7 GB |
| wan2.2_vae.safetensors | models/vae | 1.4 GB |
They start loading as soon as the rental is ready, straight from Hugging Face to the machine. Already renting an Image maker? Pick Wan 2.2 5B under Load from link on the rental's page. A card with 16 GB or more runs them.
Common questions
Questions, answered plainly.
How much VRAM does Wan 2.2 5B need?
ComfyUI, with offloading, small videos: about 8 GB; 720p, the maker's own script: about 24 GB.
Can an RTX 4090 run Wan 2.2 5B?
Yes. Wan 2.2 5B (720p, the maker's own script) needs about 24 GB, which fits in the RTX 4090's 24 GB.
Can I run Wan 2.2 5B on KernelMachine?
Yes. Rent an Image maker with these files, on this page, starts ComfyUI on the cheapest card with 16 GB or more, and the machine downloads each file from Hugging Face into ComfyUI's folders once it's ready. Already renting an Image maker? Pick Wan 2.2 5B under Load from link on the rental's page.
Other models
Compare with other image and video models.
Preparing an invite-only beta
Get an email when access opens.
No launch date is set. We'll email you once when KernelMachine opens. Nothing else.