Duplicated from jiangchengchengNLP/qwen3-4b-fp8-scaled

hhsebsb
/

qwen3-4b-fp8-scaled

compressed-tensors

Model card Files Files and versions

⚡️ Z-Image-Turbo/text-encoder FP8-static realease!

Replace the text_encoder model with an fp8 checkpoint, or drag and drop the following workflow into ComfyUI with one click:

Downloads last month: 27

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for hhsebsb/qwen3-4b-fp8-scaled

Base model

Tongyi-MAI/Z-Image-Turbo

Quantized

(93)

this model