Apple’s Product Environmental Reports put the base Mac Studio, with M5 Max, 36GB memory and 512GB storage, at 314 kg of gross greenhouse gas emissions (CO2e). The base Mac mini, with M6, 16GB memory and 256GB storage, comes in at 30 kg, and the largest single line separating them is customer product use. Both reports […]
Owners of the newest Apple devices can now fix their own hardware at home. The tech brand has officially added the iPhone 18 Pro, the M6 Mac mini, and the latest Mac Studio to its Self Service Repair program. This allows handy users to order official parts and tools directly from the company to perform […]
A drawback of using an HDR-ready third-party monitor on macOS 26 Tahoe was the inability to activate High Dynamic Range at the common 2560 x 1440 scaled resolution. Fortunately, the newest macOS release resolves this problem.
Symptom: scrolling is choppy on the Studio Display XDR at 120Hz or Adaptive (47–120Hz). At 60Hz, and on the MacBook’s own screen, scrolling is smooth.
What devices are affected: M5 Pro MacBook Pros have reproduced the problem; other repots suggest the Mac mini with M5 Pro chip is also affected. Apple lists M5 Pro MacBook Pro models as supporting the Studio Display XDR at 120Hz.
Likely cause: measurements suggest the GPU stays at a low clock speed while scrolling and misses frame deadlines.
Workaround: MacRumors Forums poster Tiguanito’s M5ScrollBoost, a small menu bar app that encourages the GPU to run faster while you scroll.
2024’s M4 Mac mini was a revelation. It packed Apple silicon power into a shockingly compact space, breathing new life into Apple’s all-time utility Mac and (eventually) making it into a go-to device for home AI and even back-end podcast transcription.
Two years later, the Mac mini gets its first update since it became such a popular purchase. It’s a bit surprising: while the high-end model has updated to the familiar M5 Pro chip found in the MacBook Pro, the lower-end model has skipped right over the M5 and become the first Mac to be released using the next-generation 2-nanometer M6 chip.
It has also, unfortunately, seen a price increase. The Mac mini famously debuted in 2005 at $499 ($855 in today’s dollars), and the M4 model was introduced at $599 in 2024 dollars. Unfortunately, after a midstream price increase and the release of this new version, the starting price has been boosted to $899, a 50% increase over that relatively recent base price.
I get it. Memory and processors are skyrocketing in price due to the AI gold rush, on top of inflation. But the fact remains that at $599, the Mac mini was about as close to an impulse buy as a Mac desktop could get. At $899, it’s crossed an invisible threshold. I can understand it, but I don’t have to like it.
Previously, on Mac mini…
The current Mac mini design is far smaller than either of the model’s two previous designs.
On the outside, this Mac mini is identical to the previous model. It’s still a 5-inch square that’s only two inches high and weighs only 1.5 pounds, a shock of a size if you’re used to the Mac mini’s pre-2024 silhouette. It’s got two USB-C ports on the front and three Thunderbolt ports on the back. (It’s Thunderbolt 4 if you’ve got the M6 model, Thunderbolt 5 for the M5 Pro.)
We’ll get to the chip momentarily, but Apple has made internal upgrades on some other Mac mini parts. Wi-Fi and Ethernet were left untouched in the 2024 Mac mini update, but not this year—the M6/M5 Pro models support Wi-Fi 7 and Bluetooth 6. Both models also come standard with 2.5Gb Ethernet, with 10Gb Ethernet as a configure-to-order option.
And now, the star of the show
The Mac mini vaulted right over the base M5 processor entirely, preventing me from making more references to that classic “Star Trek” episode where a computer tries to take Captain Kirk’s job because some A.I. genius has conned people in positions of authority into thinking that’s a good idea. (Thank goodness I have no more need to reference such outdated, irrelevant themes.)
As a result, the release of this Mac mini also marks the debut of the M6, an entirely new generation of Apple silicon that will undoubtedly populate numerous Macs and iPads over the next year. That makes it worth peeking into the details of how the M6 is structured and how it performs, even if you’re not currently in the market for a new tiny Mac.
Since the beginning, Apple’s M-series processors have included two different sets of CPU cores designed with different characteristics. The performance cores were designed to run at high speed and rip through tasks, albeit at the cost of greater power usage. (Apple would tell you that even its performance cores are also optimized to use power intelligently whenever possible, of course.) The company’s efficiency cores, on the other hand, were designed to perform lower priority low-level tasks—and computers have a lot of those!—while excelling at energy savings.
While power efficiency isn’t as important for a Mac plugged into an outlet, it’s vitally important to laptops, which make up the bulk of Apple’s Mac sales. And of course, power efficiency can also reduce thermal issues that require venting, and reduce the amount of electricity you’re paying for.
Last year, though, Apple introduced a new core type, the “super core,” with the M5. What differentiates a super core from a performance core? It comes down to the different ways computer programs do work. Software splits up tasks into individual components, or threads, and passes those to the system to send to the processor. Some software is very good at breaking up work into tiny individual components, which is good, because those tasks can be distributed across many CPU cores, where work can proceed in parallel. But some tasks aren’t broken up so readily—whether it’s because the software hasn’t been optimized, or because the task itself really is just a single big chunk that must be processed at once.
According to Apple, super cores are focused on chewing through those single-threaded tasks at maximum performance. This differentiates them from performance cores, which Apple says are tuned to perform better at complex, multi-threaded jobs. Meanwhile, those efficiency cores are percolating quietly in the background, taking care of lesser tasks that don’t require the muscle that the other two core types deliver.
In the M6, for the first time, Apple has decided to apply all three different core types to a single design: It’s got six efficiency cores, four performance cores, and two super cores. Something for every kind of task, ideally, leading to the most optimal mix of power and efficiency.
In addition, the M6 has 12 GPU cores, which pick up the neural accelerators Apple added in the M5 generation (and therefore never before seen in the Mac mini), to assist in AI jobs that run on the chip’s graphics hardware. There’s also a new dual 16-core Neural Engine, so Apple’s doubling its own home-made neural processors, all in the goal of making the M6 more impressive as a processor for AI jobs.
With these changes, the M6 ran 11% faster than the M5 in single-core CPU performance, according to my tests. That’s slightly below average for an M-series generational update, though of course if you’re specifically upgrading from any previous Mac mini, you’ll see much greater performance boosts.
In multi-core testing, the M6 performed 23% faster than the M5 generation, very slightly above average for an Apple silicon generation change.
And when it comes to GPU scores, they’re up 24% from the M5 generation—again, a very slightly above average per-generation improvement. Of course, this improvement is largely built on the back of Apple’s choice to include 12 GPU cores in the M6, up from 10 in the M5. If you divide the scores per GPU core, it suggests that Apple (quite understandably) took this generation off from massively improving its GPU core design, given the major steps forward it took in the previous two generations.
This is now part of the Apple silicon playbook. If you see Apple add GPU cores in a processor generation, it’s most likely doing so because the actual GPU cores aren’t particularly improved, so to make the chip faster, it piles in more. Increasing the GPU count by 20 percent will generally improve your GPU performance by… 20 percent. The strategy allows Apple to crow about improved GPU performance even in a year where its attention is turned elsewhere.
What’s harder to tease out in any sort of benchmark test is how the chip will perform day to day, with a varied workload. Maxing out one CPU core or all the CPU cores provides a clean answer; Apple’s three-core-type design likely works more subtly in practice. My guess is that the mix of CPU core types will result in a better balance of power and efficiency, which is essentially Apple’s holy grail when it comes to processor design. Apple wants its chips to be able to rip through a task when you need it to, but run effortlessly (and in a low-power state) the rest of the time. That’s much more difficult to measure, however.
The Apple silicon Mac era has now lasted so long that we can begin to see patterns and judge how individual generations fit into the story. The M6 processor appears to be an average improvement, so close to dead-on average that it feels like it was made specifically to meet an internal metric for improved CPU and GPU performance.
These results are colored, at least a bit, by Bloomberg’s report that Apple has decided not to ship high-end M6 processors at all, and jump directly to a new M7 generation that is better suited to “meet growing demand for on-device AI capabilities and more graphics-intensive software.” There’s nothing wrong with the M6 at all, but if Apple’s next generation chip design includes some major AI and graphics performance leaps, I can see why the company might want to prioritize that release rather than rolling out an entire chip line-up based on an adequate but uninspiring creep forward in performance.
Small is beautiful
Different footprints over the years.
Back to the Mac mini. Since Dan Moren reviewed the last two releases of this product, I haven’t gotten a chance to spend much time with it, or to write about it in detail.
Let me be clear: I love it.
I’ve been using Mac minis since the very beginning. I’ve had a Mac mini in my home as a server for most of its existence as a product.
But thanks to Apple silicon, it has gotten a new lease on life—and a new design. The fact that the Mac mini became a hot product in the last year just warms my heart. It’s always been Apple’s most versatile Mac, capable of performing whatever Mac jobs you want to throw at it. The smaller size just makes it that much more delightful. It’s a shame about the price, but you could say that about most tech prices these days.
Still, what a computer! Even the performance of the base M6 model is more than enough for most computing tasks that regular people will ever need. If you invested in an external display a few years ago, most likely that display is still going strong—and attaching a new Mac mini to it will just refresh everything. If you want a Mac to live in a closet and serve files and web pages and run AI agents or whatever, it’ll be great for that too.
The Mac mini has come into its own at last, and I’m glad for that. Perhaps in the next few years, prices will settle down and Apple will allow it to cross back over into territory where it’s more of an impulse buy, a “why wouldn’t you upgrade?” sort of proposition. Right now, make no mistake, it’s still a great option if there’s a tiny space for it in your life—but you’ll need to actually do the work to calculate the value it will provide you before making that decision.
Lançado em 2022 e disponível em mercados selecionados, o Self Service Repair permite que consumidores adquiram peças genuínas de dispositivos da Maçã e as ferramentas adequadas para realizar manutenções por conta própria, além de oferecer manuais de reparo.
No caso dos iPhones supracitados, agora é possível comprar itens como vidro traseiro, bateria, alto-falante inferior, alto-falante superior, câmera traseira, câmera frontal, tela, carcaça, placa lógica, microfone principal, bandeja do cartão, Taptic Engine e outros componentes.
No caso da nova geração do Mac Studio, é possível comprar peças como portas Thunderbolt e USB-C, ventoinhas, alto-falante, módulo de SSD, placa lógica e fonte de energia.
Como assinalado pelo 9to5Mac, o Mac mini tem uma lista mais enxuta de peças disponíveis do que os demais, mas ainda é possível encontrar componentes como ventoinhas, alto-falantes, placas lógicas e fontes de energia.
Ao que tudo indica, os preços dessas peças ficaram, em grande parte, inalterados em relação aos das gerações anteriores. Um módulo de câmera para os iPhones, por exemplo, segue saindo por US$250 — valor que cai para US$189,24 caso você devolva o original.
Já é possível adquirir essas peças nas lojas do Self Service Repair nos Estados Unidos, no Canadá e na Europa.
iPhone 18 Pro Max
Cores: bordô, glacial, prateado e preto Armazenamento: 256GB, 512GB, 1TB ou 2TB
NOTA DE TRANSPARÊNCIA: O MacMagazine recebe uma pequena comissão sobre vendas concluídas por meio de links deste post, mas você, como consumidor, não paga nada a mais pelos produtos/serviços ao usar os nossos links de afiliado.
An unverified Geekbench 7 result attributed to Apple’s M6 chip has appeared ahead of the new Mac mini’s September 22 release, offering an early and incomplete look at potential CPU gains. Geekbench is a synthetic benchmark designed to compare processor performance through a defined workload. Its result can be useful as a point of comparison, […]
Previstos para serem lançados na semana que vem (pelo menos nos Estados Unidos e em Portugal), os novos Mac mini e Mac Studio são alimentados com os chips M6 e M5 Ultra, respectivamente — lembrando que o mini pode ser configurado também com o M5 Pro, enquanto que o Studio de entrada vem com o chip M5 Max.
Pois os primeiros resultados de benchmarks dos dois novos processadores apresentados recentemente pela Apple surgiramhoje no banco de dados do Geekbench 7, oferecendo uma visão dos ganhos de desempenho de cada um deles.
Em ambos os casos, os resultados vistos até agora tratam apenas dos testes de CPU 1Central processing unit, ou unidade central de processamento. — os de GPU 2Graphics processing unit, ou unidade de processamento gráfico. ainda não foram divulgados.
Confira abaixo a pontuação do chip M6 e as pontuações médias do chip M5 para efeito de comparação:
Benchmark de CPU
M6
M5
Single-core
4.071 pontos
3.641 pontos
Multi-core
22.783 pontos
17.948 pontos
Se o resultado acima for preciso, o chip M6 apresenta um desempenho single-core cerca de 12% mais rápido e uma performance multi-core cerca de 27% mais rápida em comparação com o chip M5. Vale notar que o chip M6 está no novo Mac mini, enquanto as pontuações do chip M5 baseiam-se no MacBook Pro de 14 polegadas — mas o desempenho deve ser semelhante.
Na tabela abaixo está a pontuação do chip M5 Ultra de ponta, com CPU de 36 núcleos, bem como as pontuações médias do chip M3 Ultra de ponta, com CPU de 32 núcleos (já que a Apple nunca lançou um chip “M4 Ultra”).
Benchmark de CPU
M5 Ultra
M3 Ultra
Single-core
3.774 pontos
2.920 pontos
Multi-core
52.516 pontos
39.059 pontos
Se os resultados acima procederem, o chip M5 Ultra oferece um desempenho de CPU single-core cerca de 30% mais rápido e um desempenho multi-core cerca de 35% mais rápido em comparação com o M3 Ultra.
Nada mau, hein!
Mac Studio
Chip: M4 Max ou M3 Ultra Memória: 36GB, 48GB, 64GB, 96GB, 128GB, 256GB ou 512GB Armazenamento: 512GB, 1TB, 2TB, 4TB, 8TB ou 16TB
NOTA DE TRANSPARÊNCIA: O MacMagazine recebe uma pequena comissão sobre vendas concluídas por meio de links deste post, mas você, como consumidor, não paga nada mais pelos produtos/serviços usando os nossos links de afiliado.
The first unverified benchmark result for Apple's new M6 chip surfaced in the Geekbench 7 database today, offering a look at the chip's performance gains. The new Mac mini will be Apple's first device to be equipped with the M6 chip, which is 2nm.
Here is how the M6 chip scored:
Single-core CPU score: 4,071
Multi-core CPU score: 22,783
Here are the average M5 chip scores for comparison:
Single-core CPU score: 3,641
Multi-core CPU score: 17,948
If this single Geekbench 7 result is accurate, the M6 chip has up to around 12% faster single-core CPU performance and up to around 27% faster multi-core CPU performance compared to the M5 chip. Note that the M6 chip is in the new Mac mini, while the M5 chip scores are based on the 14-inch MacBook Pro, but performance should be similar.
Apple said the M6 chip has the world's fastest single-threaded CPU performance, and its 4,071 single-core score indeed tops all other Macs and PCs in the Geekbench 7 database, including the M5 Max chip (3,731) and Qualcomm's Snapdragon X2 Elite Extreme (3,396). Up to 27% faster multi-core CPU performance is in line with Apple's claim of up to 1.2× faster multi-threaded performance, so all of Apple's advertised claims hold up.
Here is where the M6 chip slots in for maximum multi-core CPU performance:
Apple announced new Mac mini and Mac Studio models last month, with both available to pre-order now. It is the first time in years that Apple has revised its two desktop Macs simultaneously, so which should you choose?
There are now two desktop Macs to choose from following the discontinuation of the Mac Pro, but the prices have moved sharply. The Mac Studio starts at $2,499 and rises to $5,499 for the M5 Ultra model, while the Mac mini starts at $899 with the M6 chip and $1,699 with the M5 Pro.
Those prices come on top of the across-the-board Mac and iPad increases Apple made in June, which took the Mac mini from $599 to $799, the M4 Pro configuration from $1,399 to $1,599, and the Mac Studio from $1,999 to $2,499. The M5 Ultra adds a further $200 to the post-June M3 Ultra price, putting it $1,500 above what the M3 Ultra cost at launch.
Our guide helps to answer the question of how to decide which of these two desktop Macs is best for you. The two machines now share a large number of key features, including:
A boxy silver aluminum enclosure with no color options
Apple's N1 chip, bringing Wi-Fi 7 and Bluetooth 6 to both machines for the first time
Neural Accelerators built into every GPU core
Hardware-accelerated ray tracing
A Media Engine with hardware-accelerated H.264, HEVC, ProRes, and ProRes RAW, plus AV1 decode
A next-generation SSD architecture that Apple says is up to twice as fast as before
64-core GPU: 96GB or 256GB unified memory
80-core GPU: 96GB, 256GB, or 512GB unified memory
256GB, 512GB, 1TB, or 2TB storage
512GB, 1TB, 2TB, 4TB, or 8TB storage
512GB, 1TB, 2TB, 4TB, or 8TB storage
1TB, 2TB, 4TB, 8TB, or 16TB storage
Video decode engine
Video decode engine
Video decode engine
Two video decode engines
Video encode engine
Video encode engine
Two video encode engines
Four video encode engines
ProRes encode and decode engine
ProRes encode and decode engine
Two ProRes encode and decode engines
Four ProRes encode and decode engines
Support for up to three displays: two at 6K 60Hz or 4K 165Hz, plus a third at 5K 60Hz over Thunderbolt or 4K 60Hz over HDMI
Support for up to three displays, all at 6K 60Hz or 4K 165Hz
Support for up to five 4K displays, four 6K displays, or two 8K displays
Support for up to eight 4K displays, eight 6K displays, or four 8K displays
Two displays per Thunderbolt port
All three displays through a single Thunderbolt port
Three rear Thunderbolt 4 ports
Three rear Thunderbolt 5 ports
Four rear Thunderbolt 5 ports
Four rear Thunderbolt 5 ports
Two front USB-C ports
Two front USB-C ports
Two front USB-C ports
Two front Thunderbolt 5 ports
Two rear USB-A ports
Two rear USB-A ports
2.5Gb Ethernet or 10Gb Ethernet port
2.5Gb Ethernet or 10Gb Ethernet port
10Gb Ethernet port
10Gb Ethernet port
SDXC card slot (UHS-II)
SDXC card slot (UHS-II)
Bottom power button
Bottom power button
Rear power button
Rear power button
Starts at $899
Starts at $1,699
Starts at $2,499
Starts at $5,499
Both enclosures carry over unchanged, so the dimensions of the two devices remain radically different, with the Mac Studio dwarfing the Mac mini in every way.
Mac mini
Mac Studio
Height
2.0 inches (5.0 cm)
3.7 inches (9.5 cm)
Width
5.0 inches (12.7 cm)
7.7 inches (19.7 cm)
Depth
5.0 inches (12.7 cm)
7.7 inches (19.7 cm)
Weight
M6: 1.5 pounds (0.67 kg)
M5 Pro: 1.6 pounds (0.73 kg)
M5 Max: 6.0 pounds (2.7 kg)
M5 Ultra: 8.0 pounds (3.6 kg)
Most customers should choose the M5 Pro Mac mini over the M5 Max Mac Studio, saving $800 on the base models. The gap widens across custom configurations, since the Mac Studio's memory and storage tiers start higher and climb further.
There is an unusual situation at the bottom of the lineup this year. The $899 Mac mini is the only machine of the four with a latest-generation chip, and the M6 is Apple's first 2nm chip. Its Dual 16-core Neural Engine, which Apple says system frameworks can drive simultaneously, is also more Neural Engine hardware than either the M5 Pro or the M5 Max provides. If your workload leans on on-device machine learning rather than sustained CPU or GPU throughput, the cheapest Mac in this comparison is not obviously the weakest one for the task. The trade-offs are Thunderbolt 4 rather than Thunderbolt 5, a 32GB memory and 2TB storage ceiling, and a single video encode engine.
You should only consider the Mac Studio if you have a professional workflow that can genuinely leverage the M5 Max or the M5 Ultra, along with the additional ports, display outputs, and memory capacity. If you need the Mac Studio, you will likely already know that you are looking for a highly powerful machine capable of supporting a specific intense workload. The M5 Ultra is Apple's first quad-die M-series chip, and its four ProRes engines, four video encode engines, and 1.2TB/s of memory bandwidth are aimed squarely at multi-stream video work and large local AI models. The 512GB memory ceiling has no equivalent anywhere else in the Mac lineup, and it is what allows models with hundreds of billions of parameters to run entirely on device.
The Mac Studio still has a superior selection of ports, with four rear Thunderbolt 5 ports on the M5 Max and six in total on the M5 Ultra, plus an SDXC card slot, USB-A, and 10Gb Ethernet as standard. This makes a practical difference for anyone working off fast external storage or camera media. The Mac mini has closed part of the distance by moving to 2.5Gb Ethernet as standard, up from Gigabit.
Clustering over Thunderbolt 5 and RDMA is not a point of difference between the two machines, since it arrived in macOS 26.2 last December and works on any Mac with Thunderbolt 5, including the M5 Pro Mac mini and the previous-generation Mac Studio. The exception is the M6 Mac mini, which has Thunderbolt 4 and cannot take part.
Both Mac mini models still cap out at three external displays, but they now reach 165Hz at 4K, up from 144Hz on the M4 generation, and the M5 Pro model drives all three through a single Thunderbolt port. For a three-display desk setup at high refresh rates, the M5 Pro Mac mini is sufficient. It is only above three displays, or at 6K and 8K, that the Mac Studio becomes necessary.
A notable exception arises at the top of the Mac mini lineup. An M5 Pro Mac mini configured with additional memory and storage moves close enough to the $2,499 Mac Studio that the comparison changes somewhat. For an increment of a few hundred dollars, the Mac Studio substitutes a chip with roughly twice the memory bandwidth, a second video encode engine, far greater display support, and headroom to 128GB of unified memory. If you are already spending heavily on a Mac mini, price the Mac Studio before committing.
If you plan to keep the machine for many years, the Mac Studio's ceiling matters more than its starting price, because it is the only one of the two that can be configured beyond 64GB of unified memory. Buyers weighing the M6 Mac mini against the M5 Pro Mac mini should note that the newer chip generation and the newer process node both sit in the cheaper machine, and that the M5 Pro's advantages are concentrated in multi-core and graphics performance rather than in longevity.
To some extent, purchasing decisions should be driven by budget, but any savings on the computer itself can be put toward a good external display such as Apple's Studio Display, which starts from $1,599 and was one of the few products spared June's price rises. An M6 Mac mini paired with a Studio Display comes to $2,498, a dollar less than a bare M5 Max Mac Studio with nothing to plug into. An M5 Pro Mac mini and a Studio Display together come to $3,298, which is $799 more than the base Mac Studio and $2,201 less than the M5 Ultra Mac Studio with no display at all.
Both machines are available to pre-order now and arrive on Tuesday, September 22, with education pricing of $799 and $1,599 on the two Mac mini models and $2,299 and $5,099 on the two Mac Studio models. Mac Studio configurations with 512GB of unified memory are not due until late October.
These are the first advertised dollar-off pre-order deals on the new Mac mini at Amazon.
Apple ‘s new M6 Mac mini can deliver up to 40% faster CPU performance, up to 4× faster AI performance, up to 2× faster graphics, and up to 2× faster storage versus the prior-generation M4 model it used for comparison (a 10-core M4 with 32GB memory and 2TB storage). Those figures come from Apple and apply to specific workloads, not every task.
Pre-order pricing can change, and stock or delivery dates may vary by configuration. If you are shopping specifically for an Amazon Mac mini deal, those three SKUs are the ones currently listed below Apple’s starting prices.
Please help support MacDailyNews — and enjoy subscriber-only articles, comments, chat, and more — by subscribing to our Substack: macdailynews.substack.com. Thank you!
With M6, Mac mini now delivers up to 4x faster AI performance, 2x faster storage and graphics, and 40 percent faster CPU performance. Everything on Mac mini with M6 feels incredibly fast, from everyday productivity tasks to agentic AI workflows. Mac mini with M5 Pro delivers even more pro-level performance to breeze through demanding projects, from video production to game development. And this new level of performance takes on business workflows with ease whether Mac mini is being used as a primary desktop or for always-on, deskside agentic computing. Both Mac mini models include Wi-Fi 7 and Bluetooth 6, as well as upgraded 2.5Gb Ethernet, with a 10Gb option available.
[…]
Mac mini with M6 starts at $899 (U.S.) and $799 (U.S.) for education.
[…]
Mac mini with M5 Pro starts at $1,699 (U.S.) and $1,599 (U.S.) for education.
The M6 tops out at 170GB/s and 32GB of unified memory, whereas the M5 Pro offers 307GB/s and up to 64GB–nearly twice the bandwidth, as well as twice the memory ceiling. That is the number to watch for AI inference, not just CPU and GPU benchmark deltas.
Here’s my attempt to put all of the RAM/SSD configurations into condensed tables, so you can see which storage and memory options are available for each chip, and how much they cost.
[…]
If you configure an M6 Mac Mini with 2 TB of storage, the SSD upgrade ($1,000) costs more than the entire base model computer ($900). So too with the 4 TB SSD upgrade for the M5 Pro Mini ($1,800 upgrade for a $1,700 computer).
Why announce (and take pre-orders) today, but not ship for a month? Perhaps Apple is using pre-orders to gauge interest and adjust its product mix. With huge prices for memory and storage, Apple does not want to build high-cost configurations that end up sitting around. Or, perhaps the “Fall iPhone” event will be a “new products” event, and Apple is clearing the decks of interesting-but-hardly-important hardware it doesn’t want distracting us from more exciting Macs (like the expected MacBook Pro “Ultra”).
The Mac mini now starts at $899, $300 over the original starting price of the M4 Mac mini when it launched in October 2024.
[…]
The Mac mini and Mac Studio support genlock over USB-C, so there’s no need for a separate sync box. Genlock is used in multi-camera shoots and virtual production to lock timing to a shared reference signal.
Apple’s newly announced M6 and M5 Pro Mac mini models still support up to three external displays, but there’s now support for higher refresh rates, according to Apple’s published technical specifications.
Now after the price hikes, the Neo starts at £699 and the Mini at £899. So to answer the question, is the best feature of the M6 Mini the price?
I don’t think so, and that’s not because of the increased price to £899 but because of the Macbook Neo. The Mac Mini used to be the computer that everyone bought to get a taste of macOS. A lot of my friends have purchased Mac Minis just because it was the cheapest way to get into a Mac. But now I think the Neo fills that role.
The Mac Mini hasn’t become a bad deal. It’s become a different kind of deal. If you already have a monitor and a keyboard, if you want real desktop performance without paying for an Macbook Pro or a Mac Studio, the M6 Mac Mini is still probably the best price-per-performance computer Apple sells.
Apple surprised everyone with a late August announcement of the M6 and M5 Ultra chips, along with updated Mac mini and Mac Studio models. The new Macs deliver substantial performance gains—but at prices that have increased even since June.
Earlier today, Apple unveiled the new generation of Mac mini and Mac Studio, featuring the latest entries in the Apple silicon family of chips: the M6, available in the Mac mini, and the M5 Ultra, exclusive to the Mac Studio. You can read more details about the announcement and related specs in John’s overview.
As someone who’s been working with an M3 Ultra Mac Studio (on loan from Apple) with 512 GB of RAM for the past year (plus two separate M4 Mac minis) with a particular focus on local AI models and performance gains enabled by Apple’s MLX framework, I obviously am very interested in these new machines. To give you some context: my current workspace for my upcoming iOS and iPadOS 27 review, which lives in Notion, is entirely managed by a series of local agents running the latest DeepSeek-V4-Flash via MLX on the Mac Studio, which continuously scan the project for new notes, sources, and research material that is automatically categorized and linked in the chapters that I’m writing. So, yes, I’m sure I’ll have more thoughts on the new Mac minis and Mac Studios soon. In the meantime, I thought it’d be fun to break down the local AI-related details from Apple.
First, the M6. While it may not be the powerhouse that the M5 Ultra is, it’s an interesting new chip because of its new 2 nm process and dual Neural Engine system:
M6 is built using cutting-edge 2 nm process technology, packing greater transistor density into a smaller die for a major leap in performance and power efficiency. M6 also introduces a Dual 16-core Neural Engine, providing up to 2x the peak compute over previous generations to make on-device AI workflows run even faster. System frameworks can automatically utilize both engines simultaneously, enabling applications to see faster model execution.
But that’s not all: the new 12-core GPU (which has two more cores than the M4’s old GPU) now features Neural Accelerators in each core for the first time on the Mac mini. The result, according to Apple, is “4x faster AI performance and 2x faster graphics than Mac mini with M4”. If these numbers hold up and scale linearly, a local Mixture-of-Experts model such as Qwen 3.5-35B-A3B, which would run at ~17 tokens/sec on average on a base M4 Mac mini with 16 GB of RAM, could realistically generate output at over 60 tokens/second with the base model M6 Mac mini.
Based on what we’ve seen so far, the one downside of the M6 Mac mini is that it does not have Thunderbolt 5 ports; those are exclusive to the M5 Pro model, also announced today. As Apple also notes, Thunderbolt 5 allows multiple M5 Pro Mac minis to run local AI models as a single cluster (for example, using something like exo). Alas, that won’t be possible with the M6 Mac mini and its Thunderbolt 4 bandwidth bottleneck. Nonetheless, I’d be intrigued to compare the performance of the widely regarded Qwen3.8-27B and DeepSeek-V4-Flash models on the new M6 Mac mini.
Moving on to the flagship M5 Ultra Mac Studio, let’s start here:
With M5 Ultra, Mac Studio achieves up to 4.3x the peak AI compute performance of M3 Ultra and a staggering 9.8x more than M1 Ultra. Combined with up to 512GB of unified memory and 1.2TB/s of memory bandwidth, 50 percent higher than before, Mac Studio lets users run massive models entirely on device with complete privacy — without counting tokens or worrying about rising cloud costs.
As seen on the Mac Studio’s product page, the 512 GB RAM version of the M5 Ultra Mac Studio will only be available in “late October”. Unlike the M6, the M5 Ultra supports Thunderbolt 5, which will allow customers to run multiple Mac Studios in a cluster with shared memory to distribute inference across machines. And, according to Apple, a cluster of four Mac Studios yields three times the performance of a single Mac Studio.
Speaking from personal experience, I know that my M3 Ultra Mac Studio using oMLX can run DeepSeek-V4-Flash locally with generation averaging 35 tokens/second. Assuming a linear 4x increase, that would put the same model at over 120 tokens/second on an M5 Ultra Mac Studio. To put things in perspective, that kind of performance would be faster than any AI chatbot website, it’d be faster than many providers who offer a “fast” mode for their models, and it’d only be second to either dedicated NVIDIA PC clusters at home or specialized inference providers such as Cerebras or Groq…which are running in full-blown data centers. Sure, you would need a computer that is likely going to cost more than $20,000 to make it happen, but it’d still be possible on a single machine that is small, quiet, and that – in theory – any consumer can buy off the shelf.
It’s also interesting to consider the implications of M5 Ultra for running much larger models that would have typically required aggressive quantization to even stay in memory and produce any useful output. For example, Z.ai’s GLM-5.2 (a 744B MoE model) could run at up to 17 tokens/second on an M3 Ultra Mac Studio with 512 GB of RAM; the same person was even able to get the massive Kimi K3 model to run on a single machine…with decoding performance up to 3 tokens/second. You see where this is going: by continuing to push the envelope of what is possible with M-series chips, Apple is gradually making it possible to run frontier open-weight models on local hardware that takes up as much space as four Mac minis stacked together.
Obviously, for now, this is all theoretical: we’re going to need actual benchmarks to objectively measure the improvements and performance gains of the new chips. But if Apple’s claims hold up – and I have no reason to believe they won’t – I believe both the M6 and M5 Ultra will meaningfully shake up the landscape of local AI models on macOS, reinforcing, once again, that Apple continues making the best computers for AI in the industry.
Today, Apple announced a new M6 chip that will debut in the Mac mini and an M5 Ultra that is coming to the Mac Studio. The company also announced an M5 Pro Mac mini and an M5 Max Mac Studio. Let’s take a look at the headline specs.
The headline feature of the M6 chip is that it’s Apple’s first 2-nanometer chip. The chip also includes “a larger 12-core CPU complex with the world’s fastest CPU core, a larger 12-core GPU with Neural Accelerators, a Dual 16-core Neural Engine, and up to 170GB/s of unified memory bandwidth.”
Looking more closely at the M6, Apple says it consists of two super cores, four performance cores, and six efficiency cores and is 1.2x faster in multithreaded performance than an M5 and up to 2.4x faster than an M1. Apple says the GPU delivers nearly 30% more peak GPU compute for AI than the M5. The M6’s 10% faster memory bandwidth will help with AI tasks, too, but its 32GB memory ceiling will limit which models can run locally.
Source: Apple.
The M6 mini’s GPU sounds impressive, too, with two more cores, Neural Accelerators for each core, which is a first for the mini. According to Apple, that leads to an up to four-fold increase in AI performance and a 2x graphics bump compared to the M4 mini. The Neural Engine has also been improved.
Apple also introduced an M5 Pro mini. It’s understandable if you find it confusing that the base model Mac mini has a more recent generation chipset than the more expensive model. What matters more than the chip generation is the “Pro” in M5 Pro, which makes it more capable than the M6, which has been designed for entry-level models. The same sort of asymmetry occurred with the 2025 Mac Studio, which included an M4 Max model alongside the M3 Ultra. A big part of that difference is the M5 Pro mini’s support for 64GB of memory (double the M6 version’s top memory spec) and its 307GB/s of memory bandwidth compared to the M6 model’s 170GB/s memory bandwidth.
Source: Apple.
As for the M5 Ultra, which debuts in the Mac Studio, it sounds like a beast. According to Apple, the chip uses a next-generation version of its UltraFusion technology, resulting in a quad-die architecture for the first time in an Apple silicon chip. In addition, the M5 Ultra features an “up-to-36-core CPU and up-to-80-core GPU with a massive 1.2TB/s of unified memory bandwidth, 50 percent more than M3 Ultra.”
Today, we’re debuting the next giant leap in performance and AI compute for Apple silicon with the incredibly advanced M6 and the most powerful M-series chip yet, M5 Ultra. Built using the cutting-edge 2 nm process, M6 combines a new CPU complex, two additional CPU and GPU cores, a Dual 16-core Neural Engine, and more unified memory bandwidth to power through workloads with amazing energy efficiency. And for the ultimate desktop performance and the ability to run massive AI models, M5 Ultra features a massive GPU, now with Neural Accelerators, and more unified memory bandwidth, pushing the boundaries of what a desktop can do.
Apple is fusing two dual-die M5 Max chips to create a single quad-die architecture. Apple says the M5 Ultra is “up to 1.25x higher single-threaded performance and up to 1.3x higher multithreaded performance than M3 Ultra”, the fastest Mac previously for sale. The M5 Ultra also supports up to an 80-core GPU with up to 4.5x the peak GPU compute for AI tasks compared to the M3 Ultra and features an upgraded Media Engine, according to Apple.
Source: Apple.
For those who don’t need the bleeding-edge performance of the M5 Ultra, Apple also introduced what sounds like a very capable M5 Max Mac Studio. The M5 Max version of the computer “features an 18-core CPU, an up-to-40-core GPU with Neural Accelerators built into each core, and up to 128GB of unified memory, accelerating complex pro and AI workloads.”
Macs featuring the new chips won’t be available immediately. You can preorder both online today for delivery on September 22 with the caveat that the M5 Ultra Mac Studio with 512GB of memory won’t be available until later in October.
Prices have risen too. The Mac mini models are both $100 more than the models they replace, while the M5 Ultra Mac Studio’s base configuration has risen $200. However, the M5 Max Mac Studio’s starting price hasn’t changed.
The Mac mini has been a lot of things to a lot of people over the years. From a compact, minimalist desktop system to a headless server, the mini is Apple’s jack-of-all-trades. More recently, demand for the tiny computer has surged as people put them to work for a variety of AI tasks, including running LLMs locally and serving as standalone Hermes and OpenClaw machines.
With memory and storage constraints, it’s no surprise that the base prices of the mini have risen. Despite those challenges, I hope Apple is able to produce enough to meet demand. I’ve loved having an M4 Pro model working away day and night in the background. It’s fast, relatively cool, energy efficient, and easy to run remotely. If the claims of Apple’s press release hold up under real-world use, I expect the new models will be the same, but faster and more capable, which is especially important for tasks like running models locally.
I’m also looking forward to seeing how the new Mac Studios perform in real world tests. I’ve used an M1 Max Mac Studio for a few years now and it’s been every bit the workhorse computer I need for my day-to-day work. However, it’s beginning to show its age when it comes to AI tasks, coding, and other tasks. It may finally be time for me to upgrade.
Há dois meses, falamos aqui sobre o RetinaDesk, um site muito bacana que ajuda você a escolher o melhor monitor externo para o seu Mac, levando em conta todas as especificidades dos computadores da Apple.
Pois bem, recentemente, a ferramenta ficou ainda mais completa com a adição de uma página que ajuda você a descobrir, de maneira extremamente intuitiva, a quantidade máxima de displays externos suportados pela sua máquina.
O banco de dados da ferramenta cobre todos os Macs com Apple Silicon lançados até hoje, bem como suas respectivas variantes — detalhe que joga o total de computadores listados pelo RetinaDesk para nada menos que 53.
Encontrar essa página é fácil: basta acessar o site do RetinaDesk, clicar na aba “Tools” na parte de cima da tela e, depois, selecionar a opção “Mac External Display Support by Chip” — ou simplesmente acessar esse link. Feito isso, é só selecionar o modelo do seu Mac na seção “Which Mac is it?” e, em seguida, sua respectiva variante — indicada pelo chip e o ano de lançamento (e, às vezes, o número de portas do computador) — em “Step 2”.
Captura de tela/RetinaDesk
Uma vez que você indicar o modelo do seu Mac, o número máximo de monitores externos ao qual ele pode ser conectado deverá aparecer à direita da tela, junto de uma ilustração do seu “setup máximo” — ou seja, com o maior número de monitores possível.
A nova página, no entanto, não para por aí, já que ela também conta com outra seção a qual ajuda você a montar setups com diferentes combinações de monitores, os quais podem ter resoluções e taxas de atualização distintas — sempre levando em conta, é claro, as limitações do seu computador. Ela também é uma boa forma de descobrir se o seu Mac suporta uma resolução ou uma taxa de atualização (ou uma combinação dessas duas coisas) específica.
Captura de tela/RetinaDesk
A seção “What each built-in port can drive”, por sua vez, exibe com quais resoluções/taxas de atualização cada porta do seu computador é compatível, além de revelar a sua versão (se é Thunderbolt 4 ou 5, por exemplo). Logo abaixo, temos a seção “How you can arrange the displays” que, como seu nome indica, mostra todas as combinações possíveis de monitores para a sua máquina.
Por fim, a ferramenta também deixa você comparar um Mac qualquer com outro modelo da sua escolha, checar se sua máquina precisa estar no modo clamshell para suportar um setup específico e aprender sobre soluções alternativas e suas respectivas concessões.
Captura de tela/RetinaDesk
Assim como o resto das ferramentas do RetinaDesk, essa nova página é totalmente gratuita, com o único “porém” sendo o fato de que ela não está disponível em português — problema que, é claro, pode ser facilmente remediado com a ajuda das ferramentas de tradução dos navegadores atuais.
Login
