ComfyUI Node
Llama.cpp Model Profile
Bundles model-dependent handler and sampling defaults into one typed connection.
Llama.cpp Model Profile
- model profile
◄profileGeneral►
◄custom_handlerauto►
◄temperature0.20►
◄top_p0.95►
◄top_k40►
◄min_p0.05►
◄repeat_penalty1.00►
◄presence_penalty0.00►
CategoryOllama/llama_cpp/compact
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| profile | COMBO | General | 7 options: General, Gemma 4 Vision, Muse Glimmer, Qwen 3.5 Thinking, Qwen 3.5 Non-thinking, Qwen 3 VL, +1 |
| custom_handler | COMBO | auto | 6 options: auto, generic, gemma4, qwen3_vl, qwen25_vl, qwen3_asr |
| temperature | FLOAT | 0.200–5 | — |
| top_p | FLOAT | 0.950–1 | — |
| top_k | INT | 400–10000 | — |
| min_p | FLOAT | 0.050–1 | — |
| repeat_penalty | FLOAT | 1.000–5 | — |
| presence_penalty | FLOAT | 0.00-2–2 | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| model profile | OLLAMA_IMAGE_LIST_LLAMA_CPP_MODEL_PROFILE | — |