← Back to post

Edit history

Most recent

You could include energy usage in the equation, but if you’re buying a $10,000 Mac Studio to edit your PDFs and watch YouTube, then that’s your own decision. That’s also not what we’re talking about here.

The Mac is still going to be incredibly energy efficient.

Let’s break it down for Qwen 3.5 MoE.

  • M4 Ultra Mac Studio:
    • 22t/s
    • ~ 210Wh
    • 9.55 watts per token/s
  • B300 GPU:
    • ~ 2160t/s per GPU
    • ~ 1750Wh (14Kwh 8 GPU System)
    • 0.88 watts per tokens/s

The Mac Studio comes out using ~ 11-12x more energy per token. Making it extremely energy inefficient at this task in comparison.

Edited

You could include energy usage in the equation, but if you’re buying a $10,000 Mac Studio to edit your PDFs and watch YouTube, then that’s your own decision. That’s also not what we’re talking about here.

The energy usage is going to be watts per token/s.

Let’s break it down for Qwen 3.5 MoE.

  • M4 Ultra Mac Studio:
    • 22t/s
    • ~ 210Wh
    • 9.55 watts per token/s
  • B300 GPU:
    • ~ 2160t/s per GPU
    • ~ 1750Wh (14Kwh 8 GPU System)
    • 0.88 watts per tokens/s

The Mac Studio comes out using ~ 11-12x more energy per token. Making it incredibly energy inefficient at this task

Original

You could include energy usage in the equation, but if you’re buying a $10,000 Mac Studio to edit your PDFs and watch YouTube, then that’s your own decision. That’s also not what we’re talking about here.

The energy usage is going to be watts per token/s.

Let’s break it down for Qwen 3.5 MoE.

  • M4 Ultra Mac Studio:
    • 22t/s
    • ~ 210Wh
    • 9.55 watts per token/s
  • B300 GPU:
    • ~ 2160t/s per GPU
    • ~ 1750Wh (14Kwh 8 GPU System)
    • 0.88 watts per tokens/s

The Mac Studio comes out using ~ 11x more energy per token. Making it incredibly energy inefficient at this task