inference on your head mistral 7b (4bit quantized) running locally on apple vision pro

I’m crazy jealous of your vr typing abilities lol

Making it audio -> audio, and adjusting the models for speech rather than reading output would be magical

Next step is to run LLM in neurallink

How?

App Store/github link?

Now make it work with voice and it’s a banger

it looks cool. Is it really immersive or do you feel the weight of the device on your head?

@varunshenoy_

@MatthewBerman @ollama @joaomdmoura