alt Hacker NewsApple introduces M6 and M5 Ultra for a big leap in performance and AI compute
Comments
Even w/the pricing spike, inflation adjusted we are back to roughly the prices of a new Mac SE/30 for something that can beat a turing test w/o sweating.
I yield the floor to no one when it comes to pessimism, but that's incredible.
I run a lot of local models (I am always experimenting) on my 32G M2-Pro MacMini - I would love to upgrade.
The financial aspects don’t work however: I can learn and experiment with what I have for local models, and I pay as I go on FireWorks.ai for open model inferencing and no matter how much I use this service my monthly bill is between $10 and $40 and much faster than any reasonable home rig.
Hybrid ‘small local’ and buying inference is the way I choose.
Apple Studio with maxed out M5 Ultra, 256GB RAM and 16TB storage is 18,299$. The 512GB RAM version apparently is coming in October, considering that the difference between 96GB and 256GB is priced at 4000$, the 512GB upgrade must be eye watering.
So, on the mini the RAM upgrade runs at 25$ per GB on all tiers, the same as the Studio therefore the upgrade to 512 will probably cost 6400$.
The fully maxed out Apple Studio then will be 24699$. It's 17199$ if you don't upgrade the storage(1TB).
Nevertheless I itch to have one :)
More validated by the day that my $450 M4 Mac Mini (16GB) was the best deal in computing for a long, long time.
Rumors say that Apple will only release M6 base variant and skips M6 Pro, M6 Max and M6 Ultra variants to concentrate all efforts to create a good AI capable M7:
"According to reports from Bloomberg, Apple will be skipping its M6 Pro, M6 Max, and M6 Ultra chips to accelerate development of the M7 chip. That means the only chip to be released from the M6 family will be the base M6.
The reason for this break with tradition: AI. Apple had been planning major neural-processing upgrades for the M7 family and ultimately decided those improvements were important enough to justify accelerating the next generation rather than completing the M6 lineup." https://9to5mac.com/2026/08/08/apple-m7-chip-heres-why-it-ma...
I'd skip M5 and M6 chips for LLM work and wait for a year for M7.
Apple still has the best hardware so I moved to it for the last few years, but the closed software ecosystem is terrible for taking advantage of it.
I wasn't able to debug network errors (restartin my Mac worked), Metal was missing low level disassembly / debugging tools (there is some hard to use UI), but the worst thing was the inflexible windowing system.
Even getting all the window handles on all screens/desktops with their titles and programs is impossible.
I just decided that I move to Omarchy 4 (basically Hyperland + QuickShell) + NVIDIA GPU, and I already was able to customize it more than my Mac in years.
I will miss Apple's hardware for sure, but not MacOS and the missing hardware documentation
The 512GB Ultra is amazing, sure. But who is it for exactly? VC funded big spender founders? In that case why would they need local AI? The ultra rich enthusiast? But there can't be too many of those. So who actually buys these?
Leasing now an option, only $50/month (cheaper than inference subscription?), so even cash-poor can go the amortized-investment route.
I've often felt there is tremendous value locked up in underutilized old computers. It would be interesting to see Apple in 3 years offering compute as a service using lease returns (or more likely, partnering with someone else to operate it (perhaps exclusively in secondary markets like China or India, to address political demands for local siting or jobs). Apple is in the best position to work around or even gap-fix older software/hardware limitations in a controlled environment, and now they can do so without cannibalizing new hardware sales.
>fluid frame rates in demanding games like Mixtape.
not getting on that bandwagon but wasn't that not the most demanding game as its a just a nonstop cutscene.
The M6 is useless for AI. Is there any model which is actually useful and fast on 32GB?
I somehow find it better to give 2 frontier model companies 100-200/month than dropping 10 grand on a hardware that will get old in no time with bad TPS. I really want to have a fully local model but seems like one more generation wait and we will be there?
The page says 170G/s memory bandwidth for the NPU and 1.2T/s for the GPU. Why the discrepancy if it's all "unified memory"? The former is nothing to write home about as far as AI compute is. The latter is really nice.
Which one is it you can run local models on? I suppose the NPU only.
96GB -> 256GB upgrade costs 4000 GBP in UK or $5460. $34 for GB.
In US its $4000 upgade so $25 for 1GB.
Also:
> 512GB memory option for M5 Ultra coming late October
I was just comparing this to an rtx6000 96gb build and when the f*ck did nvidia double the price?
If you want to comfortably afford this gen you had to trade options on memory stocks...
Can anyone recommend the perfect sweet spot for someone who wants to run their own inference?
I bought a 128GB M4 Max Mac Studio a while back, and for a while I thought like I had done really well to buy it when I did.
The problem I'm having now is that no models are targeting RAM of that size. Everything is either much smaller, targeting laptops, or much larger, targeting hardware well out of reach of enthusiasts.
Please, AI people, start making models targeting 128GB machines again. The last interesting one was Qwen 3.5 122B.
Call me when Linux will be officially supported. After that I can look and see what else can I get for the price and maybe then ...
FWIW scaling up from https://huggingface.co/avlp12/Qwen3.8-27B-Alis-MLX-6bit and some other sources:
You might expect the M5 Ultra to produce 50 t/s from Qwen 3.8 27B with a good context length.
Tangential, but what would be the ideal Mac option for home movie editing, casual gaming and amateur CAD fiddling in Fusion?
I plan on maximizing my residual student benefits, and taking advantage of education pricing.
Very well timed for John Ternus's first quarter.
Interesting that "coding" is now part of the marketing brochure as one of the use cases, while that was historically kind of missing. Is this new?
Damn. I just bought a maxed out MacBook Pro M5 Max 128GB 8TB, still waiting for it to be delivered. I could get 256GB RAM M5 Ultra 1TB for roughly the same price, and it's double the memory bandwidth. Which one would you recommend? I do plan to run local LLMs.
Gonna go sell a kidney, should just about cover a base Mac Studio. Guess I'll need a payday loan for the power cable
~12k for 80 core gpu with 256gb, 14k in October for 512gb. Seems like that could make for a very descent on prem inference server.
Sick. Particularly stoked for the 10gb network card ($100 option) when using the Mac Mini as a server. Just wish the memory + NVMe prices could come back down to pre ai-goldrush prices. As $2999 for the M5 Pro with 64GB RAM feels painfully over-priced.
If I compare to like, January 2024, the prices for RAM these days make me want to weep.
Maxed out Studio is $30,000+ tax in Canada if financed through Apple.
That's wild!
I would love to see real LLM performance benchmarks for these machines. Apple statement regarding LLM performance seem little vague.
I have Mac M1 Max and I'm quite happy with it. But these advances make me think that maybe I should upgrade to Mac M6 (or something) when it is released.
Every time Intel/AMD gets close enough, Apple just crushed competition in terms of SoC. I don’t know who’s on that chip team but they’re world-class. Hope they get paid more than a bunch of AI idiots Meta hired to do absolutely nothing (but I know they are not even close).
M5 Pro in a Mac Mini with 64GB RAM and 10Gbit Ethernet seems like the perfect Jellyfin server and Ollama test server. All for just over $3K (I specced with only 1TB local nvme).
Wouldn’t it be amazing for Apple to give us a MacBook Air 15” M6 with a 15W sustained passive TDP capability?
Just amazing engineering push, the competition got the message and we benefit.
0% APR for 12 months (24 for iPhones only?) from Apple Financial Services for a device that can approach or even exceed what we were paying for new cars just a few years ago. Apple is definitely making bank off these financing offers, and with very little risk as unlike a car these Mac Studios don’t lose 20% of their value when you drive them off the lot.
Interesting times, to say the least!
A Macbook Neo with an M6 and 16 GB RAM at $699/€699 would be a killer feat
Saw a 768GB RAM mac coming soon, would wait for that.
When will Apple's Mx CPUs use Intel's 18A/18A-P/14A node(s)?
From what I’ve noticed, Apple products have been getting worse in quality year after year. Sometimes they even ruin their own devices with updates... I guess it’s all because of marketing.
When is the m6 air coming though
> M6 supports up to 32GB of unified memory to multitask across demanding apps
I can't believe that Apple still comes with this bullshit like 32 GBs is a lot. It's a lot for video memory - vRAM, but not RAM.
Is Apple just going to announce everything silently from now on? No more getting excited for the big events to see what's new -- it just appears on the blog randomly?
I should have bought a 100 m4 mac minis when I had the chance. Thanks hyperscalers for buying all the supply and renting it back.
A m4 mac mini is better than al of these per dollar, msrp adjusted.
Hopefully by the end of the decade China figures out manufacturing at scale and fixes this.
> M5 Ultra features a massive amount of high-bandwidth unified memory, up to 512GB, and delivers a staggering 1.2TB/s of unified memory bandwidth that is 50 percent higher than M3 Ultra.
Apple never needed to participate in the AI race to zero. Because they were already at the finish line years ago building their own chips that can run large >100B parameter AI models locally.
yesterday someone posted a link saying xiaomi "matched" apple's latest M series performance. Was that for less than 24 hours?
will be great fun if one M5 Ultra with 512GB memory at 1.2T bandwidth capable of doing 3x smallish local model inferencing each at Opus 4.5 level of intelligence.
Well said
I know, this is a bit of a meaningless comment, but it's funny in a way. Feels like late 90s again: