The original GPT4 may have been around that size (16x 110B). But it's pretty cle... | Hacker News

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

		qeternity on April 18, 2024 \| parent \| context \| favorite \| on: Meta Llama 3 The original GPT4 may have been around that size (16x 110B). But it's pretty clear GPT4 Turbo is a smaller and heavily quantized model.

IceHegel on April 19, 2024 [–]

Yeah, it’s not even close to doing inference on 1.8T weights for turbo queries.

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