Video · Released Jul 2025
Alibaba Wan 2.2 T2V A14B
Alibaba's largest open Wan model, a two-expert mixture that swaps between a high-noise and a low-noise transformer partway through denoising. Highest quality of the local Wan entries and by far the heaviest.
From Alibaba, Wan 2.2 T2V A14B is an open-weight video-generation model. It produces short video clips from a text prompt. It runs entirely on your own hardware through GGML: no API key and no per-use fees.
Supported OS
macOSWindowsLinux
Minimum machine configuration
Local video (experimental) · 32 GB+ RAM · 28 GB disk · impractically slow without a high-end CUDA GPU
Download size · 22 GB
Specs
- Released
- 1 year ago (Jul 2025)
- Pricing
- Free, runs on your hardware
About the creator
Alibaba
Alibaba's Tongyi research group publishes the Wan video models and the Qwen family of language models.
www.alibabacloud.com ↗More from Alibaba
Wan 2.7
ImageCloud
High-quality diffusion model for detailed, prompt-faithful image generation.
Wan 2.7 Pro
ImageCloud
Alibaba's professional-grade Wan 2.7 image model for higher-fidelity, prompt-faithful generation and editing.
Qwen Image 2
ImageCloud
Alibaba Qwen's next-gen image model with native 2K resolution, professional typography, and unified generation and editing.
Qwen Image 2 Pro
ImageCloud
Alibaba Qwen's professional-grade image model for top-tier typography, photorealism, and precise multi-image editing.
Qwen Image 3
ImageCloud
Alibaba Qwen's unified image generation and editing model, balancing visual quality, layout fidelity, and speed.
Qwen Image 3 Pro
ImageCloud
Alibaba Qwen's professional-grade image model for dense layouts, small-text rendering, and multilingual visual design.