ComfyUI Node
VRGDG Unload Gemma/GGUF Models
Unloads cached VRGDG GGUF/Gemma llama.cpp models and optionally clears CUDA cache.
VRGDG Unload Gemma/GGUF Models
- status
◄clear_cuda_cachetrue►
◄clear_hf_pipeline_cachefalse►
CategoryVRGDG/LLM
Inputs (2)
| Name | Type | Default | Description |
|---|---|---|---|
| clear_cuda_cache | BOOLEAN | true | — |
| clear_hf_pipeline_cache | BOOLEAN | false | Usually leave this off. Turn it on only if you also want to clear non-GGUF local LLM pipeline caches. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| status | STRING | — |