comfyui_LLM_party

comfyui_LLM_party requires a minimum of 128MB (0.1GB) of VRAM for base operation. For optimal performance, a GPU with at least 4GB of VRAM is recommended. This node supports low VRAM mode for resource-constrained setups.

✅ RTX 3060 (12GB): Yes, fully compatible with 10.7GB headroom. ✅ RTX 4070 (12GB): Yes, fully compatible with 10.7GB headroom. ✅ RTX 4070 Ti (16GB): Yes, fully compatible with 14.3GB headroom. ✅ RTX 4090 (24GB): Yes, fully compatible with 21.5GB headroom

To run comfyui_LLM_party, you need to install: accelerate, aisuite, arxiv, attrdict, beautifulsoup4, bitsandbytes, charset_normalizer, cpm_kernels, diskcache, docstring_parser, docx2txt, easyocr, faiss-cpu, fastapi, feedparser, ffmpeg-python, fish_audio_sdk, html2image, html5lib, httpx<=0.27.2, json-repair, keyboard, langchain, langchain_community, langchain_ollama, langchain_openai, langchain_text_splitters, librosa, llama_index, markdown, markdownify, mcp, mdtex2html, moviepy, neo4j, openai>=1.57.4, openpyxl, optimum, pandas, pdfplumber, peft, psutil, py-cpuinfo, pydub, pytz, qwen-vl-utils, redis, requests, requests_toolbelt, scipy, selenium, sentence_transformers, sounddevice, soundfile, srt, streamlit, tabulate, tenacity, tiktoken, timm, transformers, transformers_stream_generator, uvicorn, verovio, virtualenv, websocket-client, wikipedia, xlrd. You can install these using pip or add them to your requirements.txt file.

comfyui_LLM_party supports low VRAM mode. To reduce memory usage: (1) Enable --lowvram or --medvram flags in ComfyUI, (2) Reduce batch size to 1, (3) Use fp16 or fp8 precision if supported, (4) Close other GPU applications.

To install comfyui_LLM_party: (1) Navigate to your ComfyUI/custom_nodes directory, (2) Clone the repository: git clone https://github.com/heshengtao/comfyui_LLM_party, (3) Install dependencies: pip install -r requirements.txt (if present), (4) Restart ComfyUI. Alternatively, use ComfyUI Manager for one-click installation.