I have never seen speeds exceed 150MB/s in real life (hundred 50)... nowhere near the 5,000 MB/s this MacBook Pro 16 with M1 Pro is supposed to be capable of.
So I am guessing that this raw speed is highly theoretical and probably only applies to specialist software applications, ie, moving editing.
Otherwise, the file system overhead prevents these numbers from getting anywhere even close to 1,000.
Unless this was in Mbit/s... which I doubt.. MB is usually Megabyte (8x Megabit)...
Try it - copy a folder with 100k items and see how it performs.
I have no problems with SSD speed by the way - in day to day, that's never a bottleneck. Only when really copying very large folders does the progress dialog even pop up. Most of the time everything is instant.
No offence, but it sounds like you don't understand much about this topic. First of all, you say "copy" but you aren't even specifying what drive you are copying to. Do you realize that the copy speed will be limited by the write speed of the drive your are copying to? No matter what the speed of the source drive is. Since you have never gotten faster than 150 MB/s, it sounds like you are copying to a spinning HDD. Even ancient SATA 2.5" SSDs could get 500-600 MB/s.
Second of all, since the switch to APFS, when you duplicate a file (different from "copying" a file but it sounds like you may be conflating the two) no data is actually copied, so it is instant.
Thirdly, it is hardly news that copying 100s of thousands of small files is much slower than copying a few large files. Just as random 4K reads and writes are much slower than 1MB sequential reads and writes. And different queue depths affect performance too. But generally, a drive capable of 7000 MB/s for sequential reads will also be much faster at 4K random reads than a drive capable of only 3000 of 1400 sequential. So it is still relevant, even if both numbers will be under 1000. It would be best if reviewers actually posted benchmark results from something like Amorphous DiskMark, which actually measures 4K random R/W and different queue depths etc. and that is something that I have been advocating for as much as possible.
If Apple's nand speeds are going to be all over the map, it might be best to buy from Apple, try and return if the speed sucks. How many times will Apple allow returns per item? The Tom's Hardware test is using 2TB MacBook M2 versions that Apple sent them. Are they using faster chips in the 2TB models than the low spec (and Mac Mini) models?
Where did 9-5 Mac get those low BlackMagic 14"M2 Pro MB (3150 MB/s) test scores compared to Matt Talks Tech (6300 MB/s)? Supposedly they both used 512GB models.
If one buys the 1TB M2 regular or Pro Mac Mini will it have BlackMagic scores in the 6000 MB/s range or the 3200 MB/s range?
I don't think the speeds are all over the map. I think Matt tech talks is sloppy and a bit of a loon. I have not seen anyone formally able to corroborate his results, yet have seen many unconfirmed (ie users with the machines posting in forums, comments etc) results that match up with what makes sense: that the 2 chip 512GB M2 Pros are around 3000 and the 4 chip 1TB and higher ones are 6000. He also keeps referring to the SSDs as "hard drives" and talks about them "spinning up" etc. He doesn't seem to know what he's talking about. I think his comments can be safely disregarded. It sounds like he was comparing a higher than 512GB 14" to a 512GB mini and is too sloppy to realize, or chose his wording very poorly. All the results I have seen outside of his have been very consistent (albeit sometimes disappointing).
In any event, when we get some formal benchmarks of the 512GB M2 Pro we will know for sure, but I would be surprised if Matt's results are anything more than a mistake or miscommunication on his part. I will be looking forward to www.notebookcheck.net 's reviews which are always very thorough and will be posted near the end of next week. They also will likely properly test the WiFi 6E performance. Unlike these other somewhat idiotic reviewers whose tests amount to "I tested the wifi 6E on my 400 down/20 up home internet connection and it was slightly faster". Talk about face palm.
Comments
Second of all, since the switch to APFS, when you duplicate a file (different from "copying" a file but it sounds like you may be conflating the two) no data is actually copied, so it is instant.
Thirdly, it is hardly news that copying 100s of thousands of small files is much slower than copying a few large files. Just as random 4K reads and writes are much slower than 1MB sequential reads and writes. And different queue depths affect performance too. But generally, a drive capable of 7000 MB/s for sequential reads will also be much faster at 4K random reads than a drive capable of only 3000 of 1400 sequential. So it is still relevant, even if both numbers will be under 1000. It would be best if reviewers actually posted benchmark results from something like Amorphous DiskMark, which actually measures 4K random R/W and different queue depths etc. and that is something that I have been advocating for as much as possible.
In any event, when we get some formal benchmarks of the 512GB M2 Pro we will know for sure, but I would be surprised if Matt's results are anything more than a mistake or miscommunication on his part. I will be looking forward to www.notebookcheck.net 's reviews which are always very thorough and will be posted near the end of next week. They also will likely properly test the WiFi 6E performance. Unlike these other somewhat idiotic reviewers whose tests amount to "I tested the wifi 6E on my 400 down/20 up home internet connection and it was slightly faster". Talk about face palm.