Qwen Image INT8 ConvRot — ComfyUI Ready

INT8 ConvRot quantized versions of Qwen-Image-2512, Qwen-Image-Edit-2511, and their shared Qwen2.5-VL-7B text encoder for use in ComfyUI. Quantized using silveroxides/convert_to_quant.

Roughly half the VRAM of the BF16 originals with no meaningful quality loss.

What's Included

File	Description	Folder
`qwen_image_2512_int8_convrot.safetensors`	Qwen-Image-2512 diffusion model	`diffusion_models/`
`qwen_image_edit_2511_int8_convrot.safetensors`	Qwen-Image-Edit-2511 diffusion model	`diffusion_models/`
`qwen_2.5_vl_7b_int8_convrot.safetensors`	Qwen2.5-VL-7B text encoder	`text_encoders/`

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for Winnougan/Qwen-Image-INT8

Base model

Qwen/Qwen-Image-2512

Finetuned

(31)

this model