Next-Generation MacBook Pros Rumored to Feature 'Very High-Bandwidth' RAM

Apple's next-generation 14-inch and 16-inch MacBook Pro models with M2 Pro and M2 Max chips will be equipped with "very high-bandwidth, high-speed RAM," according to information shared by MacRumors Forums member Amethyst, who accurately revealed details about the Mac Studio and Studio Display before those products were announced.

14 vs 16 inch mbp m2 pro and max feature 1
The current 14-inch and 16-inch MacBook Pro models are equipped with LPDDR5 RAM from Samsung, with the M1 Pro chip providing up to 200 GB/s of memory bandwidth and the M1 Max chip topping out at 400 GB/s. On a speculative basis, it is possible that the next MacBook Pro models could be equipped with Samsung's latest LPDDR5X RAM for up to 33% increased memory bandwidth with up to 20% less power consumption. This would result in up to 300 GB/s memory bandwidth for the M2 Pro and up to 600 GB/s for the M2 Max.

Bloomberg's Mark Gurman expects the next MacBook Pros to have few other changes beyond the M2 Pro and M2 Max chips. At this point, it seems likely that the laptops will be announced in November at the earliest with press releases on the Apple Newsroom site. Apple has launched new Macs in November multiple times in recent years, including the original 16-inch MacBook Pro in 2019 and the first three Macs with the M1 chip in 2020.

The current 14-inch and 16-inch MacBook Pro models with the M1 Pro and M1 Max chips were released in October 2021 and featured a complete redesign with a notch in the display and additional ports like HDMI, MagSafe, and an SD card reader.

Related Roundup: MacBook Pro
Buyer's Guide: MacBook Pro (Neutral)
Related Forum: MacBook Pro

Popular Stories

iOS 18

Here Are Apple's Full iOS 18.5 Release Notes

Tuesday May 6, 2025 2:17 pm PDT by
Apple today seeded the release candidate version of iOS 18.5 to developers and public beta testers, giving us a look at the final version of the update that will be provided to the public next week. With the release candidate, Apple provided release notes, so we have a more complete look at the new features that are included in the update, including those that weren't found during the beta...
siri glow

iPhone Users Now Able to Submit Claims in $95 Million Siri Spying Lawsuit

Wednesday May 7, 2025 11:40 am PDT by
If you owned a Siri-compatible device and had an accidental Siri activation between September 17, 2014 and December 31, 2024, you could be eligible for a payment from Apple as part of a class action lawsuit settlement. Apple in January agreed to pay $95 million to settle a class action lawsuit involving Siri spying accusations, and a website to distribute the funds has now been set up and...
iPhone 17 Pro Blue Feature Tighter Crop

iPhone 17: What's New With the Cameras

Friday May 2, 2025 3:52 pm PDT by
We've still got months to go before the new iPhone 17 models come out, but a combination of dummy models and leaks have given us some insight into what we can expect in terms of camera changes. Apple is adding new camera features, and changing the design of the camera bump for some models. You might be skeptical of dummy models, but over the years, they've proven to be a highly accurate...
iOS 18

Apple Says iOS 18.5 Coming Soon, Here is What's New

Monday May 5, 2025 8:19 am PDT by
In its press release for the new Pride Band today, Apple said that iOS 18.5 is "upcoming," following more than a month of beta testing. We expect the iOS 18.5 Release Candidate to be released this week, and this should be the final beta version, barring any last-minute bugs or changes. The software update should then be released to the general public next week. iOS 18.5 is a relatively...
Foldable iPhone 2023 Feature Homescreen

Foldable iPhone Said to Have Two Key Advantages

Monday May 5, 2025 6:41 am PDT by
Apple plans to release its first foldable iPhone next year, according to several reporters and analysts who cover the company. In his Power On newsletter today, Bloomberg's Mark Gurman said the foldable iPhone will offer two key advantages over other foldable smartphones. First, he said the foldable iPhone will have a "nearly invisible" crease when unfolded. This means the device's...
Nineth iOS 19 Feature

iOS 19 Beta is a Month Away With These New Features for Your iPhone

Thursday May 8, 2025 7:37 am PDT by
The first iOS 19 beta is just one month away, and there are already many new features and changes that are expected with it. Apple should seed the first iOS 19 beta to developers immediately following the WWDC 2025 keynote, which is scheduled for Monday, June 9. Following beta testing, the update should be released to the general public in September. Below, we recap the key iOS 19 rumors...
Foldable iPhone 2023 Feature Homescreen

Apple's Foldable iPhone Display Tech May Set New Industry Standard

Thursday May 8, 2025 3:29 am PDT by
Apple's upcoming foldable iPhone will feature a new type of display panel developed by Samsung that has never been used in a foldable product, claims a source with links to Apple's supply chain. According to the account yeux1122 on the Korean Naver blog, the foldable iPhone will use a custom display process for which Apple will hold branding trademark rights, and that meets Apple's stringent ...
AirPods Pro 3 Mock Feature

AirPods Pro 3 Just Months Away – Here's What We Know

Tuesday April 29, 2025 1:30 am PDT by
Despite being more than two years old, Apple's AirPods Pro 2 still dominate the premium wireless‑earbud space, thanks to a potent mix of top‑tier audio, class‑leading noise cancellation, and Apple's habit of delivering major new features through software updates. With AirPods Pro 3 widely expected to arrive in 2025, prospective buyers now face a familiar dilemma: snap up the proven...

Top Rated Comments

roach1245 Avatar
33 months ago
Some notes on memory bandwidth of the Apple Silicon machines (which is already extremely high) vs the new Ryzen / Intel CPUs that were released a few days / weeks ago:

Ran a simple benchmark on a new Ryzen 7950x desktop build (64GB RAM) here in the lab (the build will be returned to the supplier) vs my M1 Max laptop (64GB RAM).

Task: Take about 10000 parquet files (10.6GB total) and append them into 1 dataframe (> 400 million observations) in memory.

Hypothesis: The Ryzen 7950x should be way faster - at first thought - because it has 16 cores (versus 8 M1 Max performance cores) that are also clocked way higher.

Result: They are equally as fast because the Ryzen CPU is bottlenecked by memory bandwidth (very fast cores but just 2 memory channels on the CPU).

The files:




The task is most efficiently done in parallel using all cores available, used both polars (Rust ) and pandas-modin (C++) to do this as fast as possible.

When using all 8 performance cores on my M1 Max, memory bandwidth to CPU is at about 120 GB/s (theoretical max is 200Gb/s).




Yet the Ryzen 7950x can do 81 GB/s memory bandwidth at most as the memory runs at 5200MT/s (* 8 bytes * 2 memory channels)/1024 = 81.25 GB/s (you can stretch this to about 100 GB/s if you heavily overclock). Thus despite the 7950x's 16 faster cores it's as fast as my M1 Max with 10 cores in this task because about 6 Ryzen cores are enough to reach that 81GB/s of bandwidth. The other 10 cores are starved from input and just idling.

This is not new; others have ran similar tasks with similar results. E.g. https://tlkh.dev/benchmarking-the-apple-m1-max who finds that

"... adding more cores on the 5600X does not help (2 cores are enough to maximize memory bandwidth), while 10 cores on the M1 Max is the optimal configuration".

The M1 Ultra has 20 cores and 400GB/s of memory bandwidth and thus runs way faster than the Ryzen 7950X as none of its 20 cores are starved. This is even more so when the Ryzen 7950X is decked out with 128GB of DDR5 RAM instead (4 DIMM slots) and therefore runs at a slower 3600 MT/s instead which is a meager 56.25 GB/s memory bandwidth. 5 Ryzen cores can fully consume that; the other 11 cores will just idle.

This is also iterated at http://hrtapps.com/blogs/20220427/ which similarly highlights the importance of memory bandwidth (in computational fluid dynamics in this case) and finds that:

"M1 Ultra has an extremely high 800 GB/sec memory bandwidth.... which leads to a level of CPU performance scaling that I don’t even see on supercomputers, and is the result of a SoC (system on a chip) design"

The new Intel Raptor Lake CPUs also only have 2 memory channels and top out at about 120GB/s max memory bandwidth (heavily overclockded) as well so there won't be a difference here.

So just a heads up: the new Ryzen/Intel CPUs are good for gaming and workflows which are not so much memory dependent, but if you're doing data analysis or other scientific HPC work of some sort that is CPU-and-memory bound (thus not GPU machine learning) you'll very quickly run into memory bandwidth limits. Then you better stick to Apple's M1 / M2 chips or the AMD / Intel CPUs with more than 2 memory channels and thus more memory bandwidth (which are also way more expensive, e.g. the AMD ThreadRipper Pro 5965WX with 26 cores and 8 memory channels at 200GB/s memory bandwidth max for which you have to pay $2400 just for the chip itself and $1000 for a compatible motherboard).
Score: 73 Votes (Like | Disagree)
TheYayAreaLiving ?️ Avatar
33 months ago

Also 'very high prices'
Prices not so high. Remembering the golden era. Apple Online Store, 2002.

Attachment Image
Score: 30 Votes (Like | Disagree)
applicious84 Avatar
33 months ago

Some notes on memory bandwidth of the Apple Silicon machines (which is already extremely high) vs the new Ryzen / Intel CPUs that were released a few days / weeks ago:

Ran a simple benchmark on a new Ryzen 7950x desktop build (64GB RAM) here in the lab (the build will be returned to the supplier) vs my M1 Max laptop (64GB RAM).

Task: Take about 1000 parquet files (10.6GB total) and append them into 1 file (> 400 million observations).

Hypothesis: The Ryzen 7950x should be way faster - at first thought - because it has 16 cores (versus 8 M1 Max performance cores) that are also clocked way higher.

Result: They are equally as fast because the Ryzen CPU is bottlenecked by memory bandwidth (very fast cores but just 2 memory channels on the CPU).

The files:




The task is most efficiently done in parallel using all cores available, used both polars (Rust ) and pandas-modin (C++) to do this as fast as possible.

When using all 8 performance cores on my M1 Max, memory bandwidth to CPU is at about 120 GB/s (theoretical max is 200Gb/s).




Yet the Ryzen 7950x can do 81 GB/s memory bandwidth at most as the memory runs at 5200MT/s (* 8 bytes * 2 memory channels)/1024 = 81.25 GB/s (you can stretch this to about 100 GB/s if you heavily overclock). Thus despite the 7950x's 16 faster cores it's as fast as my M1 Max with 10 cores in this task because about 6 Ryzen cores are enough to reach that 81GB/s of bandwidth. The other 10 cores are starved from input and just idling.

This is not new; others have ran similar tasks with similar results. E.g. https://tlkh.dev/benchmarking-the-apple-m1-max who finds that

"... adding more cores on the 5600X does not help (2 cores are enough to maximize memory bandwidth), while 10 cores on the M1 Max is the optimal configuration".

Or what was referred to earlier: http://hrtapps.com/blogs/20220427/ ('http://hrtapps.com/blogs/20220427/').

The M1 Ultra has 20 cores and 400GB/s of memory bandwidth and thus runs way faster than the Ryzen 7950X as none of its 20 cores are starved. This is even more so when the Ryzen 7950X is decked out with 128GB of DDR5 RAM instead (4 DIMM slots) and therefore runs at a slower 3600 MT/s instead which is a meager 56.25 GB/s memory bandwidth. 5 Ryzen cores can fully consume that; the other 11 cores will just idle.

The new Intel Raptor Lake CPUs also only have 2 memory channels and top out at about 100GB/s max memory bandwidth as well so there won't be a difference here.

So just a heads up: the new Ryzen/Intel CPUs are good for gaming and workflows which are not so much memory dependent, but if you're doing data analysis or other scientific HPC work of some sort that is CPU-and-memory bound (thus not GPU machine learning) you'll very quickly run into memory bandwidth limits. Then you better stick to Apple's M1 / M2 chips or the AMD / Intel CPUs with more than 2 memory channels and thus more memory bandwidth (which are also way more expensive, e.g. the AMD ThreadRipper Pro 5965WX with 26 cores and 8 memory channels at 200GB/s memory bandwidth max for which you have to pay $2400 just for the chip itself and $1000 for a compatible motherboard).
You do realize this forum is for fanboys and not tech nerds, right? I'll read this on Anand Tech and Tom's Hardware, my friend ;)

Oh, and much appreciated. Nice post :)
Score: 17 Votes (Like | Disagree)
Lakersfan74 Avatar
33 months ago
Waiting for no need to upgrade from M1 posts.
Score: 16 Votes (Like | Disagree)
Mrkevinfinnerty Avatar
33 months ago
Also 'very high prices'
Score: 13 Votes (Like | Disagree)
temende Avatar
33 months ago
Nice improvement, but what matters more is memory latency, not bandwidth.
Score: 11 Votes (Like | Disagree)