logoalt Hacker News

ololobusyesterday at 7:48 PM2 repliesview on HN

I was looking at $10k Mac Studio with M5 Ultra and 256 GB for local experiments, but then struggled to find what really good modern model I can fit into it. Yes, it can run a good dense 27B at Q8 with plenty of context, but what beyond that? IIUC, some Deepseek flash variants at Q4 are also feasible, but I am not sure if the quality will be good. They also don’t run that fast, like about 30 t/s

So if I stay within 35B, especially MOE, my M5 Pro 64GB MBP can also run them well, and it can do plenty of other stuff too including gaming. While 256 GB with such RAM bandwidth and powerful GPU sounds like fun on paper, it doesn’t seem to be the next level compared to 64 GB

Really curious what people run on 256 GB Macs


Replies

vablingsyesterday at 7:50 PM

I feel like for localAI t/s is less of an issue. Just make a PRD and run a ralph loop. For big slogging projects like reverse engineering, or converting a codebase to a new language it actually doesn't matter if it takes a day or seven days.

show 1 reply
vadanskyyesterday at 7:50 PM

Sounds like it's worth waiting for M7 anyways, no point investing too much right now

https://news.ycombinator.com/item?id=48676795

show 1 reply