m5 max really fixed pp with the better matmul support, im sure the m5 ultra will... | Hacker News

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

		c0rruptbytes 11 days ago \| parent \| context \| favorite \| on: My local model setup on an M4 Pro Mac Mini m5 max really fixed pp with the better matmul support, im sure the m5 ultra will be even crazier the sparks have much slower memory bandwidth is the trade off
		help

jumploops 10 days ago [–]

I believe the dgx spark is still twice as fast at prefill as the m5 max, but the ultra should get closer to parity.

Another benefit of the 2x spark setup is that you can parallelize to ~6 streams pretty efficiently.

All depends on the workflows you’re using it for.

I’m quite excited for the M7 class machines.

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