I Ran GPT-5 Against My MacBook. The Laptop Won

#1

Post by aviflombaum » Thu, Aug 28, 2025, 5:18 PM UTC

I Ran GPT-5 Against My MacBook. The Laptop Won
twitter.com

Re: I Ran GPT-5 Against My MacBook. The Laptop Won

#2

Post by aviflombaum » Thu, Aug 28, 2025, 5:18 PM UTC

I just watched a $3,000 laptop beat OpenAI’s best model at something that actually matters. Not at generating poetry or philosophical musings. Planning a real trip to Ecuador that you could book today without embarrassing yourself or blowing your budget. This wasn’t supposed to happen. TL;DR: OpenAI charges you $20/month to use GPT-5. I ran it against free models on my laptop. The laptop models didn’t just compete. They won at the stuff that actually matters. Your laptop doesn’t have shareholders. It has you.

Re: I Ran GPT-5 Against My MacBook. The Laptop Won

#3

Post by bigyabai » Thu, Aug 28, 2025, 5:41 PM UTC

aviflombaum wrote: post #2

I just watched a $3,000 laptop beat OpenAI’s best model at something that actually matters. Not at generating poetry or philosophical musings. Planning a real trip to Ecuador that you could book today without embarrassing yourself or blowing your budget. This wasn’t supposed to happen. TL;DR: OpenAI charges you $20/month to use GPT-5. I ran it against free models on my laptop. The laptop models didn’t just compete. T…

You didn't even try running a model remotely as large as GPT-5. This is like someone running Gemma 270m on a Raspberry Pi and declaring that it's faster than your Macbook.

Re: I Ran GPT-5 Against My MacBook. The Laptop Won

#4

Post by aviflombaum » Thu, Aug 28, 2025, 5:48 PM UTC

bigyabai wrote: post #3

aviflombaum wrote: post #2

I just watched a $3,000 laptop beat OpenAI’s best model at something that actually matters. Not at generating poetry or philosophical musings. Planning a real trip to Ecuador that you could book today without embarrassing yourself or blowing your budget. This wasn’t supposed to happen. TL;DR: OpenAI charges you $20/month to use GPT-5. I ran it against free models on my laptop. The laptop models didn’t just compete. T…

You didn't even try running a model remotely as large as GPT-5. This is like someone running Gemma 270m on a Raspberry Pi and declaring that it's faster than your Macbook.

What I’m saying is that a model not as large out performed in my prompt which is I imagine complex enough to cover a lot of consumers needs. Not to mention, with the right setup, it’d be easy to forward the prompts that need the foundational models through openrouter and only get charged API token prices per use.