diff --git a/CHANGELOG.md b/CHANGELOG.md
index f01f9954b..2ec55935c 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -6,6 +6,7 @@
   - [Qwen-Image-2512](https://huggingface.co/Qwen/Qwen-Image-2512)  
     Qwen-Image successor, significantly reduces the AI-generated look and adds finer natural detailils and improved text rendering  
     available in both *original*, *sdnq-svd prequantized* and *sdnq-dynamic prequantized*  variants  
+  - [Nunchaku Z-Image Turbo](https://huggingface.co/nunchaku-tech/nunchaku-z-image-turbo)  
 - **Feaures**
   - **SDNQ** now has *19 int* based and *69 float* based quantization types  
     *note*: not all are exposed via ui purely for simplicity, but all are available via api and scripts  
diff --git a/pipelines/model_z_image.py b/pipelines/model_z_image.py
index a839715e8..9f8dd51e1 100644
--- a/pipelines/model_z_image.py
+++ b/pipelines/model_z_image.py
@@ -4,6 +4,20 @@ from modules import shared, devices, sd_models, model_quant, sd_hijack_te
 from pipelines import generic
 
 
+def load_nunchaku():
+    import nunchaku
+    nunchaku_precision = nunchaku.utils.get_precision()
+    nunchaku_rank = 128
+    nunchaku_repo = f"nunchaku-tech/nunchaku-z-image-turbo/svdq-{nunchaku_precision}_r{nunchaku_rank}-z-image-turbo.safetensors"
+    shared.log.debug(f'Load module: quant=Nunchaku module=transformer repo="{nunchaku_repo}" attention={shared.opts.nunchaku_attention}')
+    transformer = nunchaku.NunchakuZImageTransformer2DModel.from_pretrained(
+        nunchaku_repo,
+        torch_dtype=devices.dtype,
+        cache_dir=shared.opts.hfcache_dir,
+    )
+    return transformer
+
+
 def load_z_image(checkpoint_info, diffusers_load_config=None):
     if diffusers_load_config is None:
         diffusers_load_config = {}
@@ -13,7 +27,11 @@ def load_z_image(checkpoint_info, diffusers_load_config=None):
     load_args, _quant_args = model_quant.get_dit_args(diffusers_load_config, allow_quant=False)
     shared.log.debug(f'Load model: type=ZImage repo="{repo_id}" config={diffusers_load_config} offload={shared.opts.diffusers_offload_mode} dtype={devices.dtype} args={diffusers_load_config}')
 
-    transformer = generic.load_transformer(repo_id, cls_name=diffusers.ZImageTransformer2DModel, load_config=diffusers_load_config)
+    if model_quant.check_nunchaku('Model'): # only available model
+        transformer = load_nunchaku()
+    else:
+        transformer = generic.load_transformer(repo_id, cls_name=diffusers.ZImageTransformer2DModel, load_config=diffusers_load_config)
+
     text_encoder = generic.load_text_encoder(repo_id, cls_name=transformers.Qwen3ForCausalLM, load_config=diffusers_load_config)
 
     pipe = diffusers.ZImagePipeline.from_pretrained(