Qwen3-4B-Q8_0.gguf not supported by CLIPLoaderGGUF (architecture mismatch)

[mastermtb]

Hi, I tried to load Qwen3-4B-Q8_0.gguf using the CLIPLoaderGGUF node and I’m getting a size mismatch error on multiple tensors (hidden_size, attention weights, embedding shapes, etc).

CLIPLoaderGGUF
Error(s) in loading state_dict for Llama2:
size mismatch for model.layers.0.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.0.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.1.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.1.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.2.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.2.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.3.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.3.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.4.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.4.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.5.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.5.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.6.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.6.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.7.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.7.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.8.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.8.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.9.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.9.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.10.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.10.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.11.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.11.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.12.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.12.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.13.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.13.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.14.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.14.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.15.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.15.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.16.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.16.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.17.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.17.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.18.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.18.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.19.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.19.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.20.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.20.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.21.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.21.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.22.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.22.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.23.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.23.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.24.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.24.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.25.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.25.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.26.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.26.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.27.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.27.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.28.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.28.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.29.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.29.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.30.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.30.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.31.input_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.layers.31.post_attention_layernorm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for model.norm.weight: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([4096]).

[m8rr]

If you are using 6.3G file size version, try this 7G version.

https://huggingface.co/jayn7/Z-Image-Turbo-GGUF

For text encoder, try this.

https://huggingface.co/worstplayer/Z-Image_Qwen_3_4b_text_encoder_GGUF

and update comfy and GGUF node

[city96]

Could you share a screenshot of your workflow and which models files you're using?
I am unable to reproduce this issue with the files from unsloth/Qwen3-4B-GGUF (which, at least based on my guess at #368 (comment) should be the same as the reference just quantized)

[evorios]

Uninstall ComfyUI-GGUF and then reinstall ComfyUI-GGUF helped me.

[staltux]

Turn out that we need to update this node AND the comfyui, not just this node
Works fine now