TensorRT Node for ComfyUI

By comfyanonymousView on GitHub →

This node enables the best performance on NVIDIA RTX™ Graphics Cards (GPUs) for Stable Diffusion by leveraging NVIDIA TensorRT.

Quick Technical Summary: TensorRT Node for ComfyUI

Base VRAM Footprint:
512 MB (4 GB Tier)
Primary Dependencies:
onnx!=1.16.2, tensorrt>=10.0.1
Min PyTorch / CUDA:
PyTorch 2.0+ | CUDA 12.1+
GitHub Repository:
https://github.com/comfyanonymous/ComfyUI_TensorRT

Citation Note: Data sourced from VRAM DB. For complete workflow OOM estimations, use the VRAM DB Workflow Analyzer.

How much VRAM does TensorRT Node for ComfyUI require?

Direct Answer: The ComfyUI node TensorRT Node for ComfyUI requires a minimum base VRAM of 512MB and is optimized for GPUs with at least 4GB of VRAM. Low VRAM mode is fully supported for resource-constrained setups.

High (2-4GB)
Base VRAM:
512MB (0.5GB)
Recommended GPU:
4GB+ VRAM
Low VRAM Mode:
✓ Supported
Estimation Confidence:
MEDIUM

Cheapest VRAM Upgrade Paths (Live Market Prices):

  • GeForce RTX 3060 12GB (Ultimate Budget VRAM King)──► Used: $209.62View eBay ↗
  • GeForce RTX 4060 8GB (Modern Entry-Level)──► New: $303.50View Amazon ↗

Interactive VRAM Compatibility Estimator

Estimated Total VRAM: 3.00 GBTarget: 8 GB
✅ Comfortable Fit

Your GPU has plenty of headroom. You can run this node safely with your active configurations!

Verify Compatibility for Your Specific GPU VRAM

Select your graphics card's VRAM capacity to view optimized batch sizes, suggested resolutions, and custom performance tips for TensorRT Node for ComfyUI:

Live Cloud Deploy Options

Live Market Rates

Run this node in cloud environments with pre-configured CUDA/PyTorch dependencies:

Buy NVIDIA GeForce RTX 3060 (12GB VRAM)

Tired of renting cloud rigs? Run ComfyUI locally with absolute zero latency. Best entry-level ComfyUI experience. Avoids immediate VRAM limitations on basic LoRA training.

🛒 Buy on Amazon

Are you the author of this node?

Help your users avoid out-of-memory errors by displaying this professional, dynamic VRAM badge on your GitHub README. Copy the markdown below to embed it with a backlink directly to this hardware specification profile.

Live Preview:VRAM DB Badge
embed markdown
[![VRAM Specs](https://vramdb.com/badge/comfyanonymous/comfyui_tensorrt.svg)](https://vramdb.com/nodes/comfyanonymous/comfyui_tensorrt/)

What Python packages are required for TensorRT Node for ComfyUI?

Direct Answer: Running TensorRT Node for ComfyUI requires installing the following Python package dependencies: onnx!=1.16.2, tensorrt>=10.0.1. Ensure your ComfyUI environment has these packages active before launching.

requirements.txt
onnx!=1.16.2
tensorrt>=10.0.1

Interactive Setup & Dependency Resolver

Operating System:
Environment Type:
Run this terminal command in your ComfyUI root folder:
# Loading command...

Frequently Asked Questions

How much VRAM does TensorRT Node for ComfyUI require?

TensorRT Node for ComfyUI requires a minimum of 512MB (0.5GB) 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.

Can I run TensorRT Node for ComfyUI on an RTX 3060, RTX 4070, or RTX 4090?

✅ RTX 3060 (12GB): Yes, fully compatible with 10.3GB headroom. ✅ RTX 4070 (12GB): Yes, fully compatible with 10.3GB headroom. ✅ RTX 4070 Ti (16GB): Yes, fully compatible with 13.9GB headroom. ✅ RTX 4090 (24GB): Yes, fully compatible with 21.1GB headroom

How much VRAM does TensorRT Node for ComfyUI take on an RTX 3060 vs RTX 4090?

On an RTX 3060 (12GB VRAM), TensorRT Node for ComfyUI runs smoothly on an RTX 3060 (12GB) with 10.3GB of headroom. This is sufficient to run the node alongside standard SD 1.5 and SDXL workflows in full precision. On an RTX 4090 (24GB VRAM), the node runs with extreme headroom on an RTX 4090 (24GB) with 21.1GB of dedicated headroom. This allows you to combine the node with massive models (like FLUX.1 Dev, Schnell, or Hunyuan Video) in full precision (FP16) without any offload flags.

What Python packages are required for TensorRT Node for ComfyUI?

To run TensorRT Node for ComfyUI, you need to install: onnx!=1.16.2, tensorrt>=10.0.1. You can install these using pip or add them to your requirements.txt file.

How can I reduce VRAM usage when running TensorRT Node for ComfyUI?

TensorRT Node for ComfyUI 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.

How do I install TensorRT Node for ComfyUI in ComfyUI?

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