Not OP but I am finding the Qwen 2.5 32b distilled with DeepSeek R1 model to be ... | Hacker News

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

		Matl on March 5, 2025 \| parent \| context \| favorite \| on: Apple M3 Ultra Not OP but I am finding the Qwen 2.5 32b distilled with DeepSeek R1 model to be a good speed/smartness ratio on the M4 Pro Mac Mini.

bastardoperator on March 6, 2025 | [–]

I'm running the same exact models.

a1o on March 5, 2025 | [–]

How much RAM?

Matl on March 6, 2025 | [–]

It takes between 22GB-37GB depending on the context size etc. from what I've observed.

a1o on March 7, 2025 | | [–]

Thanks!

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