ComfyUI Node
Safetensors -> GGUF (llama.cpp)
A ComfyUI node in Kinburg-Nodes/LLM/GGUF with 13 inputs and 3 outputs.
Safetensors -> GGUF (llama.cpp)
- gguf_path
- log
- help
◄source►
◄output_dir►
◄output_name►
◄outtypef16►
◄quantizenone►
◄quantize_binary▾►
◄quantize_binary_path►
◄llama_cpp_dir►
◄auto_clonetrue►
◄hf_token►
◄hf_download_dir►
◄keep_intermediatefalse►
◄forcefalse►
CategoryKinburg-Nodes/LLM/GGUF
Inputs (13)
| Name | Type | Default | Description |
|---|---|---|---|
| source | STRING | HF repo id ('owner/name'), a https://huggingface.co/owner/name URL, a local HF model folder, or a single .safetensors file. Windows 'Copy as path' quotes are stripped. | |
| output_dir | STRING | Folder to write the .gguf into. Created if missing. Blank -> ComfyUI/models/llm. | |
| output_name | STRING | Base filename without extension. Blank -> derived from the model name. The precision/quant tag and .gguf are added automatically. | |
| outtype | COMBO | f16 | Precision written by convert_hf_to_gguf.py. f16 is the usual base to quantize from. When quantize != none this is the intermediate. |
| quantize | COMBO | none | Optional 2nd pass with llama-quantize to shrink the model (e.g. Q4_K_M). none = keep the outtype gguf. Needs a compiled llama-quantize binary. |
| quantize_binary | COMBO | llama-quantize executable (auto-listed from ComfyUI/models/llm). Choose the placeholder to type a path in quantize_binary_path. Only used when quantize != none. | |
| quantize_binary_path | STRING | Full path to llama-quantize(.exe), used when the dropdown is the placeholder. | |
| llama_cpp_diropt | STRING | Path to a llama.cpp checkout (holds convert_hf_to_gguf.py). Blank -> use/auto-clone one under ComfyUI/models/llm/llama.cpp. | |
| auto_cloneopt | BOOLEAN | true | If no llama.cpp is found, git clone it automatically. Needs git on PATH. Clones source only (no compiled llama-quantize). |
| hf_tokenopt | STRING | HuggingFace token for gated/private repos. Leave blank for public models. | |
| hf_download_diropt | STRING | Where to download HF repos. Blank -> the default HuggingFace cache. Ignored for local sources. | |
| keep_intermediateopt | BOOLEAN | false | When quantizing, keep the intermediate outtype gguf as well as the quantized one. Off -> delete it after quantizing. |
| forceopt | BOOLEAN | false | Re-run even if the target .gguf already exists. Off -> return the existing file without redoing the work. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| gguf_path | STRING | — |
| log | STRING | — |
| help | STRING | — |