Image GGUF models
1482 GGUF models: image and video generation models (diffusion and similar), which are not language models. Sizes run from 2M to 816B parameters. The longest trained context is 1024K tokens.
About Image GGUF models
1,482 GGUF models are filed under Image: image and video generation models (diffusion and similar), which are not language models. The most downloaded are Qwen Image 2.1 Uncensored Quantized, MiniMax H3 and Z Image Turbo. Parameter counts run from 2M to 816B, and the longest trained context window is 1024K tokens.
These are image and video generation models, not language models, and they need a runtime built for them. The memory estimates on this site are rough for them. The families you will see most are Flux (278), Qwen (189) and Wan (182).
Frequently asked questions
What are Image GGUF models?
Image and video generation models (diffusion and similar), which are not language models. There are 1,482 of them on this site.
Which Image GGUF model should I start with?
The most downloaded is Qwen Image 2.1 Uncensored Quantized. Choose the size that fits your GPU, then a Q4_K_M quant unless you have memory to spare.