Hugging Face
Turns a written prompt or an image into 720P video at 24 frames a second.
- Parameters
- 5B
- Download
- 9.5 to 11 GB
- Commercial use
- Yes
Tight fit on M4 · 16 GB
Outmake picks the Q4_K_M size: a 9.5 GB download that uses 11 GB of memory.
Made with Wan 2.2 5B
See allThe rest are this month's best-liked on Civitai, shown from there; each belongs to the person who made it. Open one for its maker.
About
One model handles both text to video and image to video. Trained with curated aesthetic data labelled for lighting, composition, contrast and color tone.
Good to know
When it animates an image, the video keeps that image's shape.
Wan 2.2 was trained on 65.6% more images and 83.2% more videos than Wan 2.1.
Sources: Wan-AI/Wan2.2-TI2V-5B model card. Every line comes from one of these.
Good at
Licence
Apache 2.0. Commercial use: yes. The maker's page has the full terms.
Wan 2.2 5B runs well from a Mac with an M3 Pro and 18 GB of memory, at Q4_K_M. 48 of 59 Mac configurations run it well.
Compare with
The nearest models in size, judged for the same Mac.
Sizes
Memory is what llama.cpp's own calculator reported for each size when the catalog was built, with the app's settings. Smaller, Balanced and Best are the three sizes the store names.
Run It Anywhere
Wan 2.2 5B is an open model. For ComfyUI, with the ComfyUI-GGUF nodes installed, put one of the GGUF files in ComfyUI/models/unet.
- ComfyUIWindows, Linux, Mac
Files
On every Mac
| Mac | Size | Fit | Memory |
|---|---|---|---|
| M6 · 16 GB | Q4_K_M | Tight fit | 11 GB |
| M6 · 24 GB | Q4_K_M | Runs great | 11 GB |
| M6 · 32 GB | Q8_0 | Runs great | 13 GB |
| M5 · 16 GB | Q4_K_M | Tight fit | 11 GB |
| M5 · 24 GB | Q4_K_M | Runs great | 11 GB |
| M5 · 32 GB | Q8_0 | Runs great | 13 GB |
| M5 Pro · 24 GB | Q4_K_M | Runs great | 11 GB |
| M5 Pro · 48 GB | Q8_0 | Runs great | 13 GB |
| M5 Pro · 64 GB | Q8_0 | Runs great | 13 GB |
| M5 Max · 36 GB | Q8_0 | Runs great | 13 GB |
| M5 Max · 48 GB | Q8_0 | Runs great | 13 GB |
| M5 Max · 64 GB | Q8_0 | Runs great | 13 GB |
| M5 Max · 128 GB | Q8_0 | Runs great | 13 GB |
| M5 Ultra · 96 GB | Q8_0 | Runs great | 13 GB |
| M5 Ultra · 256 GB | Q8_0 | Runs great | 13 GB |
| M5 Ultra · 512 GB | Q8_0 | Runs great | 13 GB |
| M4 · 16 GB | Q4_K_M | Tight fit | 11 GB |
| M4 · 24 GB | Q4_K_M | Runs great | 11 GB |
| M4 · 32 GB | Q8_0 | Runs great | 13 GB |
| M4 Pro · 24 GB | Q4_K_M | Runs great | 11 GB |
| M4 Pro · 48 GB | Q8_0 | Runs great | 13 GB |
| M4 Pro · 64 GB | Q8_0 | Runs great | 13 GB |
| M4 Max · 36 GB | Q8_0 | Runs great | 13 GB |
| M4 Max · 48 GB | Q8_0 | Runs great | 13 GB |
| M4 Max · 64 GB | Q8_0 | Runs great | 13 GB |
| M4 Max · 96 GB | Q8_0 | Runs great | 13 GB |
| M4 Max · 128 GB | Q8_0 | Runs great | 13 GB |
| M3 · 8 GB | Q4_K_M | Too big | 11 GB |
| M3 · 16 GB | Q4_K_M | Tight fit | 11 GB |
| M3 · 24 GB | Q4_K_M | Runs great | 11 GB |
| M3 Pro · 18 GB | Q4_K_M | Runs well | 11 GB |
| M3 Pro · 36 GB | Q8_0 | Runs great | 13 GB |
| M3 Max · 36 GB | Q8_0 | Runs great | 13 GB |
| M3 Max · 48 GB | Q8_0 | Runs great | 13 GB |
| M3 Max · 64 GB | Q8_0 | Runs great | 13 GB |
| M3 Max · 96 GB | Q8_0 | Runs great | 13 GB |
| M3 Max · 128 GB | Q8_0 | Runs great | 13 GB |
| M3 Ultra · 96 GB | Q8_0 | Runs great | 13 GB |
| M3 Ultra · 256 GB | Q8_0 | Runs great | 13 GB |
| M3 Ultra · 512 GB | Q8_0 | Runs great | 13 GB |
| M2 · 8 GB | Q4_K_M | Too big | 11 GB |
| M2 · 16 GB | Q4_K_M | Tight fit | 11 GB |
| M2 · 24 GB | Q4_K_M | Runs great | 11 GB |
| M2 Pro · 16 GB | Q4_K_M | Tight fit | 11 GB |
| M2 Pro · 32 GB | Q8_0 | Runs great | 13 GB |
| M2 Max · 32 GB | Q8_0 | Runs great | 13 GB |
| M2 Max · 64 GB | Q8_0 | Runs great | 13 GB |
| M2 Max · 96 GB | Q8_0 | Runs great | 13 GB |
| M2 Ultra · 64 GB | Q8_0 | Runs great | 13 GB |
| M2 Ultra · 128 GB | Q8_0 | Runs great | 13 GB |
| M2 Ultra · 192 GB | Q8_0 | Runs great | 13 GB |
| M1 · 8 GB | Q4_K_M | Too big | 11 GB |
| M1 · 16 GB | Q4_K_M | Tight fit | 11 GB |
| M1 Pro · 16 GB | Q4_K_M | Tight fit | 11 GB |
| M1 Pro · 32 GB | Q8_0 | Runs great | 13 GB |
| M1 Max · 32 GB | Q8_0 | Runs great | 13 GB |
| M1 Max · 64 GB | Q8_0 | Runs great | 13 GB |
| M1 Ultra · 64 GB | Q8_0 | Runs great | 13 GB |
| M1 Ultra · 128 GB | Q8_0 | Runs great | 13 GB |
The size is the one the store offers that Mac. Constants fitted October 11, 2026; how, and how wrong.
Badge for the model card
Shows on Wan 2.2 5B's Hugging Face card which Macs run it well, linked to this page. It updates every morning.
Sizes and files are read from QuantStack/Wan2.2-TI2V-5B-GGUF on Hugging Face and checked every morning. Catalog of November 4, 2026.