This is quite impressive to be honest. The chat is answering at a speed of one w... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		yohannparis on April 23, 2024 \| parent \| context \| favorite \| on: Llama3 running locally on iPhone 15 Pro This is quite impressive to be honest. The chat is answering at a speed of one word per few/several seconds. But still, this a nice feat. Example recording for the curious: https://www.youtube.com/watch?v=nZEvUj-QTrI

sestep on April 23, 2024 | [–]

I'm so spoiled by the quality of modern closed-source models, I laughed out loud when the beginning of its answer just said [duplicate].

bezier-curve on April 29, 2024 | [–]

On my S24 Ultra, I am seeing it generate several words a second.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact