Pick a batch weight type for all eligible tensors and/or per-tensor precisions in the table below. Conversion runs after your edits are saved, producing a single output file.
Renames every matching tensor across the file — independent of the search box above.
Name
Shape
Type
Precision
Actions
No tensors match your search.
Changes saved!
📂
Drop the model file to open it
.gguf / .safetensors — copied to the local server, then opened
Open GGUF file
—
Import tensors
New zero-filled tensor
Save as…
💾
Saving file…
Starting…
The job runs in the local gguf-editor server — closing this tab does not stop it.