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


• Genlock support over USB-C for synchronizing a display with a camera, including the iPhone 17 Pro


• An HDMI port with multichannel audio output


• A 3.5mm headphone jack with support for high-impedance headphones

Beyond that, the two lines diverge on chip generation, memory capacity, ports, and external display support.

‌Mac mini‌ (M6)	‌Mac mini‌ (M5 Pro)	‌Mac Studio‌ (M5 Max)	‌Mac Studio‌ (M5 Ultra)
M6 chip	M5 Pro chip	M5 Max chip	M5 Ultra chip (two dual-die M5 Max chips joined by UltraFusion)
Made with TSMC's 2nm process	Made with TSMC's 3nm process	Made with TSMC's ‌3nm‌ process	Made with TSMC's ‌3nm‌ process
12-core CPU (2 super cores + 4 performance cores + 6 efficiency cores)	15- or 18-core CPU (up to 6 super cores + 12 performance cores)	18-core CPU (6 super cores + 12 performance cores)	30- or 36-core CPU (up to 12 super cores + 24 performance cores)
12-core GPU	16- or 20-core GPU	32- or 40-core GPU	64- or 80-core GPU
Dual 16-core Neural Engine	16-core Neural Engine	16-core Neural Engine	32-core Neural Engine
Up to 170GB/s memory bandwidth	307GB/s memory bandwidth	Up to 614GB/s memory bandwidth	1.2TB/s memory bandwidth
16GB, 24GB, or 32GB unified memory	24GB, 48GB, or 64GB unified memory	32-core GPU: 36GB unified memory 40-core GPU: 48GB, 64GB, or 128GB unified memory	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.
This article, "Mac Mini vs. Mac Studio Buyer's Guide: 20 Differences Compared" first appeared on MacRumors.com

Discuss this article in our forums

Beyond the new chips, Apple’s latest Mac mini and Mac Studio boast practical upgrades that make a meaningful difference in everyday use.

(via Cult of Mac - Your source for the latest Apple news, rumors, analysis, reviews, how-tos and deals.)

Apple (Hacker News, MacRumors):

Mac Studio with M5 Max 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. With the powerful M5 Ultra, Mac Studio scales up to a 36-core CPU, up to an 80-core GPU, and a staggering 512GB of unified memory, enabling users to run enormous LLMs entirely on device. Wi-Fi 7 and Bluetooth 6 come to Mac Studio for the first time, while Thunderbolt 5 rounds out its extensive connectivity, so users can take advantage of blazing-fast external storage, PCIe expansion chassis, and powerful hub solutions for the most intense workloads. Thunderbolt 5 also enables multiple Mac Studio systems to be clustered, bringing up to 3x faster performance for distributed AI inference when compared to a single system.

[…]

Mac Studio with M5 Max starts at $2,499 (U.S.) and $2,299 (U.S.) for education.

[…]

Mac Studio with M5 Ultra starts at $5,499 (U.S.) and $5,099 (U.S.) for education.

It’s not shipping until September 22, with the 512 GB configuration in late October.

John Gruber:

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.

[…]

It kind of stinks that there are no RAM options for the Studio between the 96 GB base and the $4,000 256 GB upgrade.

Jason Snell:

The Mac Studio is effectively the replacement for the Mac Pro, and it’s alone in offering the Ultra-class chip. Apple has positioned the Mac Studio as ideal for local AI workflows, and the new models will still be able to cluster via Thunderbolt 5 to create even larger collections of memory and performance. Apple representatives pointed out that a four-Mac Studio AI cluster, like the one I saw on display at WWDC earlier this summer, is so efficient that it can be powered from a single standard wall outlet. (They even showed us a picture of four Mac Studios plugged into a power strip that was plugged into the wall.) In an era of data center excesses, Apple is clearly leaning into the possibility of small, efficient Macs being used to do local AI work rather than relying on huge, power-hungry cloud models.

Federico Viticci:

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.

[…]

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.

Previously:

• Apple M6 and M5 Ultra
• Apple Upgrade
• Apple Hardware Price Hikes
• Apple M5 Pro and M5 Max
• Mac Studio 2025

Update (2026-08-26): John Gruber:

That upgrade is labeled “+ $300”, which makes it look as though the starting price for the 18/40-core model is $2,800. That’s the price I put in the original version of my chart.

But if you select that option, you’ll notice that the actual starting price jumps from $2,500 to $3,100 — a $600 difference, not $300. The reason is that the $2500 18/32-core version only comes with one option for RAM: 32 GB. The 18/40-core chip has three tiers for RAM: 48, 64, and 128 GB.

Update (2026-09-02): Joe Rossignol:

Apple’s press release for the new Mac Studio with M5 Max and M5 Ultra chips last week initially stated that the computer had “next-generation SSD architecture built on PCIe Gen 6.” However, as spotted by the French blog MacGeneration, Apple removed the PCIe 6.0 mention from the announcement shortly after it was published.

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.

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.

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.”

Here’s what Sri Santhanam, Apple’s vice president of Silicon Engineering Group, had to say about the new chips:

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.

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.