ComfyUI Node
Load LLM Model (GGUF)
Loads a GGUF language model for prompt enhancement. Place .gguf files in ComfyUI/models/LLM/
Load LLM Model (GGUF)
- llm_model
◄llm_modelno_models_found►
◄n_gpu_layers-1►
◄n_ctx4096►
CategoryLLM/Prompt Enhancement
Inputs (3)
| Name | Type | Default | Description |
|---|---|---|---|
| llm_model | COMBO | no_models_found | 1 options: no_models_found |
| n_gpu_layers | INT | -1-1–100 | Number of layers to offload to GPU. -1 = all layers. |
| n_ctx | INT | 4096512–32768 | Context window size in tokens. Qwen3 supports up to 40960. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| llm_model | LLM_MODEL | — |