ComfyUI-MotifVideo2B on 24GB GPU
Compatible with 24GB GPU
This node will run on RTX 3090, RTX 4090, A5000 and similar GPUs with 24GB VRAM.
Optimized Settings for 24GB
VRAM Utilization
17%
You're using 17% of your 24GB VRAM, leaving 20.0GB headroom.
Recommended Batch Size
20
Start with batch size of 20 for optimal performance.
Suggested Resolution
1024x1024 or higher
Best balance of quality and performance for 24GB.
Performance Tips
- Close other GPU-intensive applications
- 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:
- 4096MB (4.00GB)
- Your GPU (24GB):
- 24576MB (24GB) - RTX 3090, RTX 4090, A5000
- VRAM Utilization:
- 17%
- Available Headroom:
- 20.00GB
- Low VRAM Mode:
- ✗ Not supported
- Estimation Confidence:
- MEDIUM
Python Dependencies
diffusers>=0.35.2einopssentencepiece# HF README 표준 동반. GemmaTokenizerFast 는 tokenizer.json 만으로 동작하지만 transformers 의 slow-tokenizer fallback / 타 tokenizer 변형 환경에서 필요 가능성.transformers>=5.5.4