LLM Memory Calculator for Mac
Effortlessly estimate how much unified memory your Mac (M1, M2, M3, or M4 series) will use when running Hugging Face models in MLX-based workflows.
Just enter the model ID and context length and get immediate insights into memory demand, including activations and KV-cache, tailored to Apple Silicon’s unified memory architecture.
Compatible with Torch and Transformers frameworks too. Optimize your model deployment, avoid memory issues, and make the most of your Mac’s AI potential.
Not working with a model? Missing feature? Let us now:
Enter your Hugging Face model ID and context length to see unified memory usage in MLX. Get instant insights on activations and KV-cache, avoid OOMs, and run models smoothly on Apple Silicon. Also works with Torch and Transformers.
Not working with a model? Missing feature? Let us now:
Model configuration:
Enter a model ID
