Local LLM session nodes for ComfyUI that run GGUF models with llama.cpp without external runtimes like Ollama. Supports image analysis, audio analysis, user-model chat, and model-to-model dialogue across Llama, Mistral, Qwen, DeepSeek, GLM, Gemma, Phi, LLaVA, and gpt-oss with compatible backends.
https://github.com/kantan-kanto/ComfyUI-LLM-Session
git clone https://github.com/kantan-kanto/ComfyUI-LLM-Session
comfy node install comfyui-llm-session