Live data from Hacker News

MacBook Pro with M5 Pro and M5 Max

apple.com

441–450 of 1001 posts

Re: MacBook Pro with M5 Pro and M5 Max

#441
post #435

Earlier quoted context omitted.

The price hasn't changed between the M4 and M5. I honestly don't know how they did it. But I had a standing order for a maxed-out M4 (128 GB RAM, 2 TB drive) and the price is the same as the M5 so I cancelled my M4 order and will pre-order the M5 MAX instead.

Well, guess I was wrong about that.

that is ... not at all how that works. RAM is a separate chip, that is placed on top of the substrate that holds the main dies. It is bought from normal ram manufacturers like micron. it is not "embedded in the chip" by any possible meanings of those words.

Re: MacBook Pro with M5 Pro and M5 Max

#442
post #207

Earlier quoted context omitted.

What are the other specs and how's your setup look? You need a minimum of 24GB of RAM for it to run 16GB or less models.

48 GB MacBook Pro. All of the models I've tried have been slow and also offered terrible results.

Try a software called TG Pro lets you override fan settings, Apple likes to let your Mac burn in an inferno before the fans kick in. It gives me more consistent throughput. I have less RAM than you and I can run some smaller models just fine, with reasonable performance. GPT20b was one.

Re: MacBook Pro with M5 Pro and M5 Max

#443

I chased down what the "4x faster at AI tasks" was measuring: > Testing conducted by Apple in January 2026 using preproduction 13-inch and 15-inch MacBook Air systems with Apple M5, 10-core CPU, 10-core GPU, 32GB of unified memory, and 4TB SSD, and production 13-inch and 15-inch MacBook Air systems with Apple M4, 10-core CPU, 10-core GPU, 32GB of unified memory, and 2TB SSD. Time to first token measured with an 8K-to…

14-billion parameter model with 4-bit quantization seems rather small

For anyone who has been watching Apple since the iPod commercials, Apple really really has grey area in the honesty of their marketing.

And not even diehard Apple fanboys deny this.

I genuinely feel bad for people who fall for their marketing thinking they will run LLMs. Oh well, I got scammed on runescape as a child when someone said they could trim my armor... Everyone needs to learn.

Re: MacBook Pro with M5 Pro and M5 Max

#444
post #259

Earlier quoted context omitted.

If 40k is the barrier to entry for impressive, that doesn't really sell the usecase of local LLMs very well. For the same price in API calls, you could fund AI driven development across a small team for quite a long while. Whether that remains the case once those models are no longer subsidized, TBD. But as of today the comparison isn't even close.

It’s what a small business might have paid for an onprem web server a couple of decades ago before clouds caught on. I figure if a legal or medical practice saw value in LLMs it wouldn’t be a big deal to shove 50k into a closet

You would still have to do some pretty outstanding volume before that makes sense over choosing the "Enterprise" plan from OpenAI or Anthropic if data retention is the motivation.

Assuming, of course, that your legal team signs off on their assurance not to train on or store your data with said Enterprise plans.

Re: MacBook Pro with M5 Pro and M5 Max

#446

Earlier quoted context omitted.

It's not exactly a bump if they raise prices at the same time, though with the RAM situation I'm not mad.

Well 1TB MacBook Pro used to cost $1799, now 1TB is the base model and costs $1699, so it's actually a $100 price drop for 1TB storage.

Not if you compare Macbook Pro with Pro CPUs.

Re: MacBook Pro with M5 Pro and M5 Max

#447

I chased down what the "4x faster at AI tasks" was measuring: > Testing conducted by Apple in January 2026 using preproduction 13-inch and 15-inch MacBook Air systems with Apple M5, 10-core CPU, 10-core GPU, 32GB of unified memory, and 4TB SSD, and production 13-inch and 15-inch MacBook Air systems with Apple M4, 10-core CPU, 10-core GPU, 32GB of unified memory, and 2TB SSD. Time to first token measured with an 8K-to…

>Time to first token measured with an 8K-token prompt using a 14-billion parameter model with 4-bit quantization

Oh dear 14B and 4-bit quant? There are going to be a lot of embarrassed programmers who need to explain to their engineering managers why their Macbook can't reasonably run LLMs like they said it could. (This already happened at my fortune 20 company lol)

Re: MacBook Pro with M5 Pro and M5 Max

#450
post #13

The performance numbers are impressive, but I do not get the on-board AI spin. What is it used for?

Private AI assistants will be a big thing. You don't want to send all your private data they have access to to a cloud AI API provider. You shouldn't, anyway.
Post reply on HN