You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
np.uint32(41) is not a valid GGMLQuantizationType error on using bonsai_image_4b-q1_0.gguf #457
!!! Exception during processing !!! np.uint32(41) is not a valid GGMLQuantizationType
Traceback (most recent call last):
File "/home/path/ComfyUI/execution.py", line 524, 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, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/path/ComfyUI/execution.py", line 333, 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, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/path/ComfyUI/execution.py", line 307, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "/home/path/ComfyUI/execution.py", line 295, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "/home/path/ComfyUI/custom_nodes/ComfyUI-GGUF/nodes.py", line 169, in load_unet
sd, extra = gguf_sd_loader(unet_path)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/path/ComfyUI/custom_nodes/ComfyUI-GGUF/loader.py", line 74, in gguf_sd_loader
reader = gguf.GGUFReader(path)
^^^^^^^^^^^^^^^^^^^^^
File "/home/path/ComfyUI/custom_nodes/gguf/gguf_connector/reader.py", line 105, in init
self._build_tensors(offs, tensors_fields)
File "/home/path/ComfyUI/custom_nodes/gguf/gguf_connector/reader.py", line 208, in _build_tensors
ggml_type = GGMLQuantizationType(raw_dtype[0])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/path/anaconda3/envs/comfyui/lib/python3.12/enum.py", line 751, in call
return cls.new(cls, value)
^^^^^^^^^^^^^^^^^^^^^^^
File "/home/path/anaconda3/envs/comfyui/lib/python3.12/enum.py", line 1165, in new
raise ve_exc
ValueError: np.uint32(41) is not a valid GGMLQuantizationType
So i understand that the quantisation used for bonsai is Q1_0 1-bit quantization. Which is not a part of dequantisation code of the GGUF nodes. Is there a workaround for it instead of having to manually make changes? If someone has alternatives to implement this or use this model. I would like to know.
Activity
lim3light commentedon Jun 9, 2026
So i understand that the quantisation used for bonsai is Q1_0 1-bit quantization. Which is not a part of dequantisation code of the GGUF nodes. Is there a workaround for it instead of having to manually make changes? If someone has alternatives to implement this or use this model. I would like to know.