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. gpugreg · 1790003246 · focus · HN ↗
  Those RTX 5090 numbers are bad. You can get over 200 tps with ninfer using NVFP4 and MTP.
  1. beastman82 · 1790006689 · focus · HN ↗
    can confirm.
    I dont' know why people spend huge money on these and Spark. The 5090 is running qwen 3.8 at 200+ tps!! That's 1-2 orders of magnitude faster.
    mathisfun123 · 1790006888 · focus · HN ↗
    same reason they spend huge amounts of money on rolexes when seikos work better (the tech crowd isn't immune from vanity).
    throwaway27448 · 1790008593 · focus · HN ↗
    If you seriously think apple products are nothing but a status item, you're deluding yourself and probably have been for decades.
    _hugerobots_ · 1790009722 · focus · HN ↗
    This 1000%. Data centres don't equate to medium sized labs and businesses. A stack of Macs is up and running without digging trenches, an electrician on staff and a department of PhDs to justify the spend.
    bigyabai · 1790009889 · focus · HN ↗
    It's likely that a stack of Macs will draw more power for slower prefill/decode than equivalently priced Nvidia GPUs. If power efficient inference is the goal, Macs are a non-starter.
    _hugerobots_ · 1790011541 · focus · HN ↗
    So if it isn't a comparative ability, now it's a power cost issue? This reads like goal post moving.
    bigyabai · 1790020736 · focus · HN ↗
    Oh, it's absolutely both. The power you waste waiting for TFTT on prefill will absolutely compound at the "medium sized labs and businesses" scale.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.