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.
    tomega2134 · 1790013177 · focus · HN ↗
    Is a 5090 still cost efficent when it is (currently) unobtainable? Or when obtainable only at current prices (min. $6500 USD)?
    throwaway219450 · 1790022731 · focus · HN ↗
    Personally I think the price is way too high right now. It’s a power hungry gaming GPU. The efficient single card equivalent would be a 4500 Blackwell which launched at about $3500. Or you could get a 9700 32GB or an Arc B70 for well under $2k, today. You only buy a 5090 if you want absolute speed.
    32GB is still not that much. I would rather get a Spark and have the RAM to experiment with larger LLMs, even if it was slow.
    searealist · 1790037059 · focus · HN ↗
    A 5090 has 2x tensor cores and 2x bandwidth and can be run at 400W (2x watts).
    throwaway219450 · 1790050316 · focus · HN ↗
    Being fast and having a power target doesn’t mean it’s cost efficient though. I would pay the launch cost for one, but not 3-4x inflated.
    searealist · 1790055436 · focus · HN ↗
    How does this relate to 4500 vs 5090? I'm just pointing out that 5090 likely has twice the performance of the 4500 and likely maintains that at 2x watts if you want.
    throwaway219450 · 1790110519 · focus · HN ↗
    You didn't specify in your earlier post, so I wasn't sure exactly which comparison you were making. But yeah, the perf/watt actually looks the same for those, so the cost per token evens out. It is nice not having to manage 400+W though. I like the 4000 for that reason, it's effectively a 3090 that runs at half the TDP.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.