Earlier quoted context omitted.
I can’t download ms teams on Linux (the browser version sucks).
You can download ms teams on Linux, you just can't use it.
That sounds like the same problem then?
Apple introduces M6 and M5 Ultra
931–940 of 1001 posts
Re: Apple introduces M6 and M5 Ultra
#932I was blown away by M1 Pro, and used it for 4 years before it became a little sluggish, and replacing it with an Asus S16 running on Ryzen AI 9 HX 370 (an excellent laptop). One of the main reasons was missing my old Linux setup. I've briefly tested M5 Pro in an Apple store and was surprised by how quick it felt and did anything. A tangible and significant difference, and I really feel it would be good getting it, or…
I have never owned an Apple product that didn't slowly get worse over time. After a couple iPads and MacBooks, I'm almost certain they are intentionally updating their operating system to slow down older products. Even worse is the removal of access to certain applications for older hardware in the name of security or compatibility. Meanwhile my Linux laptop continues to get faster every year as the operating system…
M1 Pro here 32GB 1TB good machine but slowing down so much that I really hate it. I had Asahi on it 2 years ago but in the end had almost bricked it when I tried to reinstall. I'm running a Linux desktop well spec and am quite happy with it. But on the road and in the office I use the MBP.
I'm thinking, now that I fully gotten used to and am in love with fedora Workstation and Gnome I should give it another try maybe and see what it can do nowadays. I was holding back cause DP Alt was missing and that still seems to be an issue. but have since reduced to 1 big external monitor so even HDMI would do it. or DisplayLink.
Re: Apple introduces M6 and M5 Ultra
#933Earlier quoted context omitted.
> I'd skip M5 and M6 chips for LLM work and wait for a year for M7. Or you could lease an M5 max/ultra until the M7 equivalent comes out. At least in the US a leasing option is available.
I'd be worried about securely erasing my data when returning a leased model.
What do you do with older hardware that you've bought? Do you not wipe it and resell / donate?
If you encrypt from day one then a lease isn't much different.
Re: Apple introduces M6 and M5 Ultra
#934Earlier quoted context omitted.
> I'd skip M5 and M6 chips for LLM work and wait for a year for M7. Or you could lease an M5 max/ultra until the M7 equivalent comes out. At least in the US a leasing option is available.
I'd be worried about securely erasing my data when returning a leased model.
Just delete the encryption key.
Re: Apple introduces M6 and M5 Ultra
#935Can anyone recommend the perfect sweet spot for someone who wants to run their own inference?
I have been looking for a good local setup for a while now. Qwen 3.8 27b is really good for a dense model of this size IMO. I already had an RTX 4090 and I forked ninfer [0] with the obsession to squeeze everything out of this card for this model. Results: 149 tok/s decode speed (aggregate with concurrency about ~270 tok/s) with prefill speeds faster than 2500 tok/s. And all of this with full 262k albeit quantized context. Fast prefill speed is really important when launching multiple clients such as opencode or pi at the same time and especially if they launch subagents. This is why I also implemented a caching tier so computed contexts can be faster loaded from RAM (or disk). Speeds feel almost like with official SOTA openai or anthropic models.
Im currently measuring a pareto front in J/tok in order to set power limits of this card without sacrificing too much performance. Since we are talking about full power draw of ~480W which is fine during the day (with solar panels) but during night when the sun doesn't shine (even with a battery) I'd like to limit this a little bit.
Re: Apple introduces M6 and M5 Ultra
#936Earlier quoted context omitted.
Extraordinary claims require extraordinary evidence.
I’m mostly talking about their iPhones, where new updates sometimes make older models worse. I know a lot of people whose iPhones started lagging after iOS updates.
Hard disagree, I'm still rocking an iphone 7.
Re: Apple introduces M6 and M5 Ultra
#937Curious how the M6 neural engine compares for local LLM inference. That's the real benchmark now.
Re: Apple introduces M6 and M5 Ultra
#938Earlier quoted context omitted.
It's interesting to see how defensive some of these pro-China posters get on HN and elsewhere. I'm genuinely curious why there seems to be an inferiority complex here with respect to America/American companies.
China follows foot-in-the-door tactic per the Art of War. (done in HK, Korea, Singapore, and Malaysia) This in-turn later on, AIs will train to make pro-China comments as AIs train on these. They got the sheer man-power, and with AIs it's even easier.
I had to read it a few times to parse what you meant but now that I have, this actually makes a lot of sense.
Re: Apple introduces M6 and M5 Ultra
#939Earlier quoted context omitted.
> a little sluggish > surprised by how quick it felt Aren't these properties of the (G)UI rather than of the processor? I've been using systems 20 years ago that were super snappy. The same software would still be snappy today obviously. But the software has become bloated to the point that you need to run the latest generation of CPUs such that things are not sluggish. In principle you don't need 32-core GHz CPUs to…
> In principle you don't need 32-core GHz CPUs to move a window around on a screen without it feeling sluggish I think the snappiness is less this, and more about the speed to open a file, how quickly chrome pops open when you open it etc. I assume this is a combination of hardware and how fast SSD->RAM is due to the SOC, but software will certinaly play a big part too.
> I assume this is a combination of hardware and how fast SSD->RAM is due to the SOC, but software will certinaly play a big part too.
That is exactly what I'm talking about. Sorry, you are completely off. My machine 20 years ago was not an SOC and didn't have an SSD either. It was fast as lightning to open a window.
What does this have to do with SSD? Or an SOC? It's all because the software is incredibly bloated, and as your comment indicates, the young generation doesn't even know this and thinks the hardware is to blame because it's 2 gens behind state of the art (so, 3.5 years old).
This is very sad and exactly why things are the way they are.
Re: Apple introduces M6 and M5 Ultra
#940Earlier quoted context omitted.
I happily booted and ran an Intel Mac mini using a 4TB drive in a Thunderbolt 3 enclosure, and I do the same for an M4 Max Mac Studio using an 8TB drive in a USB4v2 enclosure (OWC Express 1M2 80G). You'll just have to be careful to match the enclosure to the ports on the system. The base-model M6 Mac mini still uses Thunderbolt 4, so a USB4v2 enclosure would be wasted.
Funnily enough I do the same with my Intel iMac... I have a 2TB Thunderbolt 3 Glyph drive as my primary and boot drive and it works a dream... if I got one of these new Mac minis without upgrading the drive, presumably I could just plug this straight into it and apple will do its magical migration thing?
These Macs are reportedly shipping with macOS 27 Golden Gate. You'd have two incompatible constraints: Macs don't like to run a version older than what they shipped with, and Golden Gate doesn't support the Intel iMac.
You might be able to boot from the internal drive, install/upgrade the external drive, then boot from it.