ComfyUI SmartLML
Smart Model Loader for ComfyUI — single node for vision-language models, text LLMs, and WD14 taggers across 8 backends (Transformers, GGUF, vLLM, SGLang, Ollama, llama.cpp, YOLO, WD14). Supports QwenVL, Mistral3, Florence-2, LLaVA, YOLO with multi-task chaining, few-shot training, and auto-download. V3 API + Nodes 2.0 compatible. NVIDIA/AMD/ROCm.
VRAM Requirements
Direct Answer: The ComfyUI node ComfyUI SmartLML requires a minimum base VRAM of 256MB and is optimized for GPUs with at least 4GB of VRAM. Low VRAM mode is fully supported for resource-constrained setups.
- Base VRAM:
- 256MB (0.3GB)
- Recommended GPU:
- 4GB+ VRAM
- Low VRAM Mode:
- ✓ Supported
- Estimation Confidence:
- HIGH
🧮 Interactive VRAM Compatibility Estimator
Your GPU has plenty of headroom. You can run this node safely with your active configurations!
Deploy on High-Performance GPUs
Need more VRAM to run ComfyUI with this node? Rent low-cost, high-performance GPUs on Vast.ai instantly.
Deploy on Cloud GPUs
Need more VRAM to run ComfyUI with this node? Rent low-cost, high-performance cloud GPUs on RunPod instantly.
Python Dependencies
Direct Answer: Running ComfyUI SmartLML requires installing the following Python package dependencies: accelerate>=0.26.0,<2.0.0, aiohttp, bitsandbytes>=0.41.0,<1.0.0, huggingface-hub>=0.20.0, llama-cpp-python>=0.3.16, numpy, onnxruntime, peft>=0.18.1, pillow, psutil, pyyaml, qwen-vl-utils# Required for Qwen2.5-VL and Qwen3-VL vision processing, requests, torch, transformers>=5.0.0, ultralytics>=8.3.162. Ensure your ComfyUI environment has these packages active before launching.
accelerate>=0.26.0,<2.0.0
aiohttp
bitsandbytes>=0.41.0,<1.0.0
huggingface-hub>=0.20.0
llama-cpp-python>=0.3.16
numpy
onnxruntime
peft>=0.18.1
pillow
psutil
pyyaml
qwen-vl-utils# Required for Qwen2.5-VL and Qwen3-VL vision processing
requests
torch
transformers>=5.0.0
ultralytics>=8.3.162🛠️ Interactive Setup & Dependency Resolver
# Loading command...