ComfyUI Node
[llama.cpp] Generate
Runs one multimodal llama.cpp completion using separate Compact model and hardware profiles plus a shared Prefill Profile and optional reasoning and speculative configs.
[llama.cpp] Generate
- model_profile
- prefill_profile
- hardware_profile
- reasoning
- speculative
- images
- audio
- video
- response
- thinking
- raw JSON
- metrics
- media diagnostics
◄model_path[no GGUF models found]►
◄mmproj_path[none]►
◄system►
◄prompt►
◄n_ctx8192►
◄max_tokens512►
◄seed-1►
◄stop►
◄video_with_audiofalse►
◄verbosefalse►
Categoryllama_cpp/compact
Inputs (18)
| Name | Type | Default | Description |
|---|---|---|---|
| model_path | COMBO | [no GGUF models found] | 1 options: [no GGUF models found] |
| mmproj_path | COMBO | [none] | 1 options: [none] |
| model_profile | OLLAMA_IMAGE_LIST_LLAMA_CPP_MODEL_PROFILE | Required output from [llama.cpp] Model Profile. | |
| prefill_profile | OLLAMA_IMAGE_LIST_LLAMA_CPP_PREFILL_PROFILE | Required output from [llama.cpp] Prefill Profile. | |
| system | STRING | — | |
| prompt | STRING | — | |
| n_ctx | INT | 8192512–1048576 | — |
| max_tokens | INT | 5121–131072 | — |
| seed | INT | -1-1–4294967295 | — |
| stop | STRING | — | |
| video_with_audio | BOOLEAN | false | When enabled, extract the first embedded video audio track with PyAV and pass it through the AUDIO input path. |
| verbose | BOOLEAN | false | — |
| hardware_profileopt | OLLAMA_IMAGE_LIST_LLAMA_CPP_HARDWARE_RUNTIME_PROFILE | Optional output from [llama.cpp] Hardware Runtime Profile. Disconnected uses Automatic Offload. | |
| reasoningopt | OLLAMA_IMAGE_LIST_LLAMA_CPP_REASONING_CONFIG | Optional output from [llama.cpp] Thinking / Reasoning Profile. Disconnected uses model-default reasoning behavior. | |
| speculativeopt | OLLAMA_IMAGE_LIST_LLAMA_CPP_SPECULATIVE_CONFIG | Optional shared output from a Compact N-gram or Native Speculative Config node. | |
| imagesopt | IMAGE | — | |
| audioopt | AUDIO | Standalone AUDIO items. Audio belonging to VIDEO stays in VIDEO. | |
| videoopt | VIDEO | VIDEO items may contain their own AUDIO components. |
Outputs (5)
| Name | Type | Description |
|---|---|---|
| response | STRING | — |
| thinking | STRING | — |
| raw JSON | STRING | — |
| metrics | STRING | — |
| media diagnostics | OLLAMA_IMAGE_LIST_LLAMA_CPP_MEDIA_DIAGNOSTICS | — |