CanIRun.ai
Break down how CanIRun.ai reads your CPU, memory and GPU through browser APIs, then grades local AI models from runs great all the way to too heavy, without installing anything.
CanIRun.ai answers the first question before running a model locally: can this machine actually handle it? Open the page and the browser reads CPU, memory, GPU VRAM and WebGPU support on the device itself, then lists the models that fit and tags each card as runs great, runs well, decent, tight fit or too heavy. Nothing about your hardware leaves the machine, and models are grouped by task such as chat, code or reasoning.