Custom Node Testing
Expected Behavior
CLIPLoaderGGUF - Unexpected text model architecture type in GGUF file: 'qwen2vl'
Actual Behavior
Attempting to load Qwen2.5-VL-7B-Instruct-GGUF in to the native gguf cliploader - https://huggingface.co/unsloth/Qwen2.5-VL-7B-Instruct-GGUF/tree/main
and this is the error I see
Steps to Reproduce
Attempting to load Qwen2.5-VL-7B-Instruct-GGUF in to the native gguf cliploader - https://huggingface.co/unsloth/Qwen2.5-VL-7B-Instruct-GGUF/tree/main
and this is the error I see
Debug Logs
2025-08-08T13:39:57.897564 - Using xformers attention in VAE
2025-08-08T13:39:57.898564 - Using xformers attention in VAE
2025-08-08T13:39:58.027056 - VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
2025-08-08T13:40:03.400756 - !!! Exception during processing !!! Unexpected text model architecture type in GGUF file: 'qwen2vl'
2025-08-08T13:40:03.401756 - Traceback (most recent call last):
File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 496, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 315, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 289, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 277, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\nodes.py", line 228, in load_clip
return (self.load_patcher([clip_path], clip_type, self.load_data([clip_path])),)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\nodes.py", line 204, in load_data
sd = gguf_clip_loader(p)
^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\loader.py", line 237, in gguf_clip_loader
sd, arch = gguf_sd_loader(path, return_arch=True, is_text_model=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\loader.py", line 84, in gguf_sd_loader
raise ValueError(f"Unexpected text model architecture type in GGUF file: {arch_str!r}")
ValueError: Unexpected text model architecture type in GGUF file: 'qwen2vl'
2025-08-08T13:40:03.402756 - Prompt executed in 5.66 secondsOther
No response
Custom Node Testing
Expected Behavior
CLIPLoaderGGUF - Unexpected text model architecture type in GGUF file: 'qwen2vl'
Actual Behavior
Attempting to load Qwen2.5-VL-7B-Instruct-GGUF in to the native gguf cliploader - https://huggingface.co/unsloth/Qwen2.5-VL-7B-Instruct-GGUF/tree/main
and this is the error I see
Steps to Reproduce
Attempting to load Qwen2.5-VL-7B-Instruct-GGUF in to the native gguf cliploader - https://huggingface.co/unsloth/Qwen2.5-VL-7B-Instruct-GGUF/tree/main
and this is the error I see
Debug Logs
Other
No response