761–770 of 1001 posts
Hot take - Local LLM computing will move to stationary, always on devices (Mac mini & studio). Developers and users will move to lighter, portable devices to interface with their long running agent workers (MacBook Airs & iPads).
Earlier quoted context omitted.
So it's not measuring output tokens/s, just how long it takes to start generating tokens. Seems we'll have to wait for independent benchmarks to get useful numbers.
It's going to be faster no matter what. My M3 MAX prints tokens faster than I can read for the new MoE models. It's the prompt processing that kills it when the context grows beyond a threshold which is easy to do in the modern agentic loops.
Earlier quoted context omitted.
Please, source this ridiculous claim
First page, first result on Google: https://andreafortuna.org/2025/11/30/hidden-metadata-reveals...
The question is when Apple Laptops are going to be able to run LLMs with a performance comparable to what the AI companies are offering?
Never - data centers will always offer more power if you only care about raw inference speed. HOWEVER I think that we'll reach the 'good enough' bar super soon. In 2-3 years I expect apple macs to be able to run a model as 'good' as Claude 4.6 sonnet at 90% of the inference speed we're used to from a cloud API. Yes, I'm sure by then there will be better models on offer via cloud providers, but idk if I'll even care.…
Honest question. Is it possible to install an earlier version of macOS on these machines? Liquid glass looks so.. unprofessional to my eyes. And I hear it's also unstable.
That's a big part of what's keeping me from upgrading. Every time I look at my wife's iPhone I'm dumbfounded by just how bad the liquid glass looks. It's the first time I've ever been so repulsed by a design that I actively avoid it just... out of sheer preference.
"Scaling up performance from M5 and offering the same breakthrough GPU architecture with a Neural Accelerator in each core, M5 Pro and M5 Max deliver up to 4x faster LLM prompt processing than M4 Pro and M4 Max, and up to 8x AI image generation than M1 Pro and M1 Max." Are they doubling down on local LLMs then? I still think Apple has a huge opportunity in privacy first LLMs but so far I'm not seeing much execution.…
I love the following section of their copy: > Even More Value for Upgraders > The new 14- and 16-inch MacBook Pro with M5 Pro and M5 Max mark a major leap for pro users. There’s never been a better time for customers to upgrade from a previous generation of MacBook Pro with Apple silicon or an Intel-based Mac. I read as "Whoops we made the M1 Macbook Pro too good, please upgrade!" I think I will get another 2-5 years…
I thought the buyer was insane to buy it at that price. But, of course mine had a decent spec and still had the Apple care warranty with very low battery cycle count. After the sale, the buyer told me the truth: The M1 is the best chip Apple ever made and I wouldn't see much of a difference in real world between the M1 Pro and an M3 Pro unless it was the Max version of the chip.
I didn't believe him then. But, after a year of being on M3 Pro, I gotta say he was spot on. Don't get me wrong, the M3 Pro is definitely faster in a lot of things. But not 3x or 2x faster like Apple always like to market. I can open a few extra tabs without slowing down, compile times (Elixir) did get somewhat faster. But definitely not faster to the point where there were two generations worth of performance improvements like Apple claimed.
The M1 chip series is vastly underrated.
Earlier quoted context omitted.
14-billion parameter model with 4-bit quantization seems rather small
I think these aren't meant to be representative of arbitrary userland-workload LLM inferences, but rather the kinds of tasks macOS might spin up a background LLM inference for. Like the Apple Intelligence stuff, or Photos auto-tagging, etc. You wouldn't want the OS to ever be spinning up a model that uses 98% of RAM, so Apple probably considers themselves to have at most 50% of RAM as working headroom for any such wo…
I love the following section of their copy: > Even More Value for Upgraders > The new 14- and 16-inch MacBook Pro with M5 Pro and M5 Max mark a major leap for pro users. There’s never been a better time for customers to upgrade from a previous generation of MacBook Pro with Apple silicon or an Intel-based Mac. I read as "Whoops we made the M1 Macbook Pro too good, please upgrade!" I think I will get another 2-5 years…
Yeah reading these announcements I realized my M1 Pro is supposed to be obsolete but I still see no reason to upgrade. Also, my wife's still using the older touch bar MBP, and we'll, it works fine for her too. I'm not sure who needs the newer pros.
I recently swapped out my work PC (a beefy workstation laptop) for an M4 Pro and it’s an amazing upgrade.
Earlier quoted context omitted.
I’m sorry you have to make do with that setup. I’d upgrade to an M5 Pro 64GB right away. In fact, your old one has no value. I can safely dispose of it for you.
Ahh I see, I just bought like few weeks ago but why would you say that