Wan GGUF models
243 GGUF models in the Wan family, quantized by 181 uploaders. Sizes run from 34M to 17.3B parameters. The longest trained context is 256K tokens.
About the Wan GGUF models
Wan is represented on ggufmodels.com by 243 GGUF models, quantized by 181 uploaders on Hugging Face. The most downloaded are Wan2.1, Wan2.2 I2V A14B and Wan2.2 TI2V 5B. Parameter counts run from 34M to 17.3B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Wan model is between 0.2 to 16.8 GB, which is the quant most people start with. Most files come from QuantStack (20), vantagewithai (6) and city96 (6). The quants you will meet most often are Q8_0 (139), Q4_K_M (123), Q6_K (121) and Q5_K_M (103), where the number is how many models offer that quant.
Frequently asked questions
Which Wan GGUF should I download?
The most downloaded Wan GGUF here is Wan2.1. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Wan model need?
Q4_K_M files of Wan models on this site range from 0.2 to 16.8 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Wan GGUF files come from?
The most common quantizers here are QuantStack, vantagewithai and city96. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.