Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

M4 MacBook Pro

apple.com

Post reply on HN
Print view View original

961–970 of 1001 posts

Re: M4 MacBook Pro

#961

Post by kristianp »

cjbprime wrote: post #751
kristianp wrote: post #725

Earlier quoted context omitted.

q4 or q5 quantization. Edit: Actually you'd want q3 to fit a 200B model into 128GB of RAM. e.g. this one is about 140GB https://huggingface.co/lmstudio-community/DeepSeek-V2.5-GGUF...

Wouldn't it be incredibly misleading to say you can interact with an LLM, when they really mean that you can lossy-compress it to like 25% size where it becomes way less useful and then interact with that? (Isn't that kind of like saying you can do real-time 4k encoding when you actually mean it can do real-time 720p encoding and then interpolate the missing pixels?)

Yes the size is much reduced, and you do have reduced quality as a result, but it isn't as bad as what you're implying. Just a few days ago Meta released q4 versions of their llama models. It's an active research topic.

Re: M4 MacBook Pro

#962

Post by xz0r »

jcmontx wrote: post #20

> "up to 1.8x faster when compared to the 16-inch MacBook Pro with M1 Pro" I insist my 2020 Macbook M1 was the best purchase I ever made

I too bought a 2020 MBA M1, it was great initially, but now seems like its getting throttled, same goes with my iPhoneX, I used to love Apple, but its just pathetic that they throttle older devices just to get users to upgrade.

Re: M4 MacBook Pro

#963

Post by Tagbert »

miahi wrote: post #865
grecy wrote: post #860

Earlier quoted context omitted.

So you're saying Apple added something to the design to make it do things faster...which is literally the definition of improvement. When a company adds a supercharger to a car does it not count as faster? When I add more solar panels to my roof does it not count as more power? Surely doing this kind of thing is exactly what we want companies to be doing to make their products faster/better.

It will be faster only for code that uses/is optimized for that specific extension. And the examples you give are not really correct. If you add a supercharger you will get more power, but if the car's transmission is not upgraded, you might just get some broken gears and shafts. If you add more solar panels to your roof, you might exceed the inverter power, and the panels will not bring benefits. It's true that you…

That is an example of the kind of hardware and software synergy that gives good performance on Apple Silicon for apps in iOS and Mac OS. Apple execs have given interviews where they talk about this kind of thing. They look at code in the OS and in their application libraries that can benefit from hardware optimization and they build in hardware support for it to improve performance overall. This helps all kinds of app running on the OS and using the standard libraries.

Re: M4 MacBook Pro

#964

Post by resters »

spease wrote: post #499
resters wrote: post #493

It's hard to imagine ay reason why I would not want to keep upgrading to a new MPB every few years -- my M3 MBP is by far the best laptop I've owned thanks to the incredible battery life. Of course I'm rooting for competition, but Apple seems to be establishing a bigger and bigger lead with each iteration.

I don’t see the yearly releases as saying you have to upgrade. Rather, having a consistent cadence makes it easier for the supply chain, and the short iteration time means there’s less pressure to rush something in half-baked or delay a release.

I agree. my comment was not meant to suggest that I believe otherwise.

Re: M4 MacBook Pro

#965

Post by resters »

telesilla wrote: post #505
resters wrote: post #493

It's hard to imagine ay reason why I would not want to keep upgrading to a new MPB every few years -- my M3 MBP is by far the best laptop I've owned thanks to the incredible battery life. Of course I'm rooting for competition, but Apple seems to be establishing a bigger and bigger lead with each iteration.

My M1 laptop from early 2022 is too good for me to care about upgrading right now, I loaded it up with 64GB ram and it's still blazing. What benefit would I really notice? My heavy apps loading a couple of seconds faster?

I agree. I also have an M1 mini with 8GB of RAM and while I wish I'd bought one with more RAM, it work nicely when the task doesn't require much RAM. The incremental benefits of the M2-M4 are nice, but they do not obsolete the M1 by any stretch of the imagination.

Re: M4 MacBook Pro

#966

Post by seec »

slmjkdbtl wrote: post #762
jcmontx wrote: post #20

> "up to 1.8x faster when compared to the 16-inch MacBook Pro with M1 Pro" I insist my 2020 Macbook M1 was the best purchase I ever made

I switched from a 2014 MacBook pro to a 2020 M1 MacBook Air, yeah the CPU is much faster, but the build quality and software is a huge step backwards. The trackpad is feels fake, not nearly as responsive, keyboard also feel not as solid. But now I'm already used to it.

They also feel very bulky/innelegant while still being fragile for the most part and not really hitting workstation level territory.

I don't understand how people are enamored with those things, sure it's better in some way than what it was before but it's also very compromised for the price.

Re: M4 MacBook Pro

#967

Post by ElCapitanMarkla »

preisschild wrote: post #948
aorth wrote: post #886

Four generations into the new platform and there is no answer from anyone else in the industry. Incredible.

I switched my work M1 Max with an AMD Ryzen 9 7940HS Framework 16 running Linux and am happier since. I guess it depends on the person which computer is better for them.

I wish I could get that option but I'm still waiting for an NZ release :(

Re: M4 MacBook Pro

#968

Post by greggroth »

preisschild wrote: post #948
aorth wrote: post #886

Four generations into the new platform and there is no answer from anyone else in the industry. Incredible.

I switched my work M1 Max with an AMD Ryzen 9 7940HS Framework 16 running Linux and am happier since. I guess it depends on the person which computer is better for them.

I'm torn between the new M4 MBP and a Framework laptop with Linux for my personal computer. Can you share some deciding factors for you? Does it mostly come down to the OS? How is the battery life with the Framework?

Re: M4 MacBook Pro

#969

Post by a012 »

flkiwi wrote: post #920
saagarjha wrote: post #809

Earlier quoted context omitted.

The Mac mini video from yesterday has employees: https://www.apple.com/105/media/us/mac-mini/2024/58e5921e-f4...

That by itself raises an interesting editorial question. Apple (like most big companies) doesn't do things randomly re: high impact public communications like this. I'm curious what made the Mac mini a product that merited showing people doing things, with a computer that is tied to one location, vs. a Macbook Pro's comparative emptiness, for a computer that can go anywhere and be with anyone. It could be as simple a…

I imagine the Mac mini is really small now if it could be powered via USB PD then I think it’s no problem to put it in a backpack with a kb and touchpad then bring it home then to the office. This is because I notice there are many people just bring their MBP to the office then plug it to a big screen. The downside is just you can’t work anywhere like with a MBP, but the usability is mostly the same (to me)

Re: M4 MacBook Pro

#970

Post by chipdart »

grecy wrote: post #860
toxicdevil wrote: post #814

Earlier quoted context omitted.

These numbers are misleading (as in not apples to apples comparison). M4 has a matrix multiply hardware extension which can accelerate code written (or compiled) specifically for this extension. Also: https://news.ycombinator.com/item?id=40339248

So you're saying Apple added something to the design to make it do things faster...which is literally the definition of improvement. When a company adds a supercharger to a car does it not count as faster? When I add more solar panels to my roof does it not count as more power? Surely doing this kind of thing is exactly what we want companies to be doing to make their products faster/better.

> So you're saying Apple added something to the design to make it do things faster...

I think the whole point is that microbenchmarks provide no data in overall performance. They just test very specific and by no means common use case.

Post reply on HN