What's my local AI?

Check what's the best model you can run locally!

Your machine

We auto-detect what we can from your browser; everything else is a best guess. Tweak any value below to see what else could run.

Hardware

GPU edited

Memory

RAM edited
VRAM edited

Platform

CPU edited
OS edited
WebGPU edited

Your local model

Apple Silicon: LM Studio also runs MLX models. Filter the catalog with lms get --mlx. Ollama also runs MLX models. Look for tags ending in -mlx. The commands on this page use GGUF via llama.cpp and Metal.

lean max performance

What next?

How detection and the estimates work