running it on my M4 @ 90tps, takes 18GB of RAM. | Hacker News

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

		jonrosner 57 days ago \| parent \| context \| favorite \| on: Nvidia Nemotron 3 Family of Models running it on my M4 @ 90tps, takes 18GB of RAM.

Tepix 56 days ago | [–]

If it uses 18GB of RAM, you're not using the official model (released in BF16 and FP8), but a quantization of unknown quality.

If you write "M4", you mean M4 and not M4 Pro or M4 Max?

pylotlight 57 days ago | [–]

M2 Max @ 17tps btw

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