Wan2.2 TI2V 5B needs about 3.7 GB of memory at Q4_K_S (a 2.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 2.9 GB (Q4_K_S) to 5.3 GB (Q8_0).
Wan2.2 TI2V 5B is a 5B-parameter Wan model in GGUF format, quantized by off-grid-ai. The repository has 2 quant files, from 2.9 GB (Q4_K_S) to 5.3 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_S | 2.9 GB | 3.7 GB | Fits | Get file → | |
| Q8_0 | 5.3 GB | 6.5 GB | Fits | Get file → |
What GPU do you need for Wan2.2 TI2V 5B?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q4_K_S (2.9 GB file, about 3.7 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_S (2.9 GB file, about 3.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.3 GB file, about 6.5 GB in use).
Which Wan2.2 TI2V 5B quant should you choose?
Q4_K_S (2.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Wan2.2 TI2V 5B
How much VRAM does Wan2.2 TI2V 5B need?
About 3.7 GB at Q4_K_S with an 8K context window. That is the 2.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Wan2.2 TI2V 5B on an 8 GB GPU?
Yes, with Q8_0: the 5.3 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Wan2.2 TI2V 5B GGUF?
It depends on the quant: Q4_K_S is 2.9 GB, Q8_0 is 5.3 GB.
Where can I download Wan2.2 TI2V 5B GGUF?
The files are on Hugging Face in the off-grid-ai/Wan2.2-TI2V-5B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Wan2.2 TI2V 5B use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.