TensorRT Node for ComfyUI on 8GB GPU
Compatible with 8GB GPU
This node will run on RTX 3060 Ti, RTX 4060 and similar GPUs with 8GB VRAM.
Optimized Settings for 8GB
VRAM Utilization
6%
You're using 6% of your 8GB VRAM, leaving 7.5GB headroom.
Recommended Batch Size
7
Start with batch size of 7 for optimal performance.
Suggested Resolution
1024x1024 or higher
Best balance of quality and performance for 8GB.
Performance Tips
- Close other GPU-intensive applications
- Low VRAM mode available
- Monitor GPU usage with nvidia-smi
🚀 Deploy ComfyUI on Vast.ai
Need low-cost, high-performance cloud GPUs to run ComfyUI and this custom node? Rent instantly on Vast.ai starting at pennies per hour.
🚀 Deploy ComfyUI on RunPod
Need high-performance cloud GPUs to run ComfyUI and this custom node? Rent instantly on RunPod starting at just a few cents per hour.
VRAM Requirements
- Base VRAM Requirement:
- 512MB (0.50GB)
- Your GPU (8GB):
- 8192MB (8GB) - RTX 3060 Ti, RTX 4060
- VRAM Utilization:
- 6%
- Available Headroom:
- 7.50GB
- Low VRAM Mode:
- ✓ Supported
- Estimation Confidence:
- MEDIUM
Python Dependencies
onnx!=1.16.2tensorrt>=10.0.1