Actually they plan to put an LLM in your back pocket using flash memory, not sil... | Hacker News

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

		quentinp on March 29, 2024 \| parent \| context \| favorite \| on: Towards 1-bit Machine Learning Models Actually they plan to put an LLM in your back pocket using flash memory, not silicon: https://arxiv.org/abs/2312.11514

declaredapple on March 29, 2024 [–]

The flash doesn't do the computations though, that's just a method of getting it to the processor

sroussey on March 29, 2024 | [–]

It would be better to have eeprom or some such directly attached as memory. No loading.

Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact