Thread

M5 Ultra Mac Studio Review

269 points · 262 comments · piotrgrabowski

simonw · 1790001122 · focus · HN ↗
The numbers I was most interested in are tucked away in a chart towards the bottom - the speed comparison of the Mac Studios v.s. a RTX 5090:
```
  Qwen3.8 27B tokens&#x2F;sec generation speed

  Prompt size    8K    64K   128K   256K
  RTX 5090 PC    59    51    44     n&#x2F;a
  M5 Ultra       48    39    32     24
  M3 Ultra       31    23.5  20     15
```
A whole bunch more comparison numbers in this section: <a href="https://www.macstories.net/stories/m5-ultra-mac-studio-review-the-dream-mac-for-local-ai-agents/#mx-pc" rel="nofollow">https://www.macstories.net/stories/m5-ultra-mac-studio-revie...
1. alex7o · 1790011470 · focus · HN ↗
  On my m5 max 27b model does 75tps on 256k ctx and starts at 80 on the 8k ctx when you add <a href="https://huggingface.co/collections/z-lab/dflash-2" rel="nofollow">https://huggingface.co/collections/z-lab/dflash-2 to it. So yeah base might be 30tps (I used iq4) but mtp or dflash help a lot and should be used when checking what is useful and what is not for running models as it is not fare to judge without them.

Unofficial Hacker News client; not affiliated with Y Combinator.