Wan2.2 T2V-A14B
Hugging Face (Wan-AI) Open weights
The catch: The A14B single-GPU command needs at least 80GB VRAM; TI2V-5B runs on 24GB (RTX 4090) and the card quotes just under 9 minutes per 5-second 720P clip.
| Access | Open weights |
|---|---|
| Free limits | Free to download and self-host; you pay only for your own compute. Wan2.2 family: T2V-A14B (text-to-video) and I2V-A14B (image-to-video) are MoE models with 27B total / 14B active parameters, making 5-second clips at 480P or 720P; TI2V-5B (5B dense) does both text- and image-to-video at 720P, 24fps. |
| Modality | video |
| Credit card | Not required |
| Commercial use | Allowed |
| Trains on your data | – |
| Licence or terms | Apache-2.0 |
| Context window | – |
| Model id | Wan-AI/Wan2.2-T2V-A14B |
| Base URL | – |
| Last checked | 2 Oct 2026 |
How to use Wan2.2 T2V-A14B
Download the weights and serve them yourself; the quickstart below shows one way. Licence: Apache-2.0.
Quickstart
huggingface-cli download Wan-AI/Wan2.2-T2V-A14B --local-dir ./Wan2.2-T2V-A14B && python generate.py --task t2v-A14B --size 1280*720 --ckpt_dir ./Wan2.2-T2V-A14B --offload_model True --convert_model_dtype --prompt "<your prompt>" # run inside github.com/Wan-Video/Wan2.2
Paste into Claude Code
I want to run the open-weight model "Wan2.2 T2V-A14B" (Wan-AI/Wan2.2-T2V-A14B) for my project. Please: 1. Check the model card and tell me the hardware it needs and the simplest way to serve it (vLLM, SGLang, Ollama or a hosted endpoint). 2. Give me a minimal working setup and a test request. 3. Tell me the licence terms for commercial use. 4. If a cheaper or smaller variant would do the job, mention it.
Before you ship on it
- The A14B single-GPU command needs at least 80GB VRAM; TI2V-5B runs on 24GB (RTX 4090) and the card quotes just under 9 minutes per 5-second 720P clip.
- Apache-2.0; the card's licence section says Wan claims no rights over generated content and lists banned uses (illegal, harmful, misinformation, targeting vulnerable groups) (huggingface.co/Wan-AI/Wan2.2-T2V-A14B).
- Free to run means you pay for the GPUs, the serving stack and the on-call.
Questions
Is Wan2.2 T2V-A14B free?
Yes. Open weights offers it as open weights, with these limits: Self-host free · Apache-2.0. No credit card is needed.
Can I use Wan2.2 T2V-A14B commercially?
Yes, under Apache-2.0. Check the current terms before you ship.
How do I start with Wan2.2 T2V-A14B?
Download the weights and serve them yourself; the quickstart below shows one way. Licence: Apache-2.0.
Source: huggingface.co/Wan-AI/Wan2.2-T2V-A14B, checked 2 Oct 2026.