Calculate exactly how much GPU memory (VRAM) you need to run any AI model locally. Supports 290+ models at FP16, Q8, Q4, and other quantization levels.
We may earn a commission from cloud and hardware partners at no extra cost to you.
VRAM estimates are approximate. Actual usage varies by model architecture, batch size, and runtime.
For MoE models (Mixtral, DeepSeek), only active parameters are loaded — actual VRAM may be lower than total parameter count suggests.