How to run LLMs locally on mobile devices (with Gemma and On-Device AI tools)

Y	Hacker News new \| ask \| show \| jobs

	How to run LLMs locally on mobile devices (with Gemma and On-Device AI tools) (annjose.com)
	1 points by annjose 373 days ago

1 comments

Any models that can run on a mobile device will likely be 8B or smaller, will have very noticable hallucination problems.