Toshiba XG3 M.2 NVMe SSD Review (1TB) – Rocket Ship NVMe SSD

CRYSTAL DISK BENCHMARK VER. 5.1.2 X64

Crystal Disk Benchmark is used to measure read and write performance through sampling of random data which is, for the most part, incompressible. Performance is virtually identical, regardless of data sample so we have included only that using random data samples.

Toshiba XG3 1TB NVMe M.2 SSD Crystal Diskmark 2

This is perhaps one of the best Crystal Diskmark results we have ever had for a small form factor SSD.  Not only does performance once again exceed listed specs (and while testing with incompressible data), but also, we get a great glimpse at that rare low 4k write disk transfer speed score above 200MB/s.

AS SSD BENCHMARK VER 1.8.5

The toughest benchmark available for solid state drives is AS SSD as it relies solely on incompressible data samples when testing performance.  For the most part, AS SSD tests can be considered the ‘worst case scenario’ in obtaining data transfer speeds and many enthusiasts like AS SSD for their needs. Transfer speeds are displayed on the left with IOPS results on the right.

Toshiba XG3 1TB NVMe M.2 SSD AS SSD BenchToshiba XG3 1TB NVMe M.2 SSD AS SSD IOPSTypically, AS SSD read and write results are a bit lower than other benchmarks, but AS SSD also demonstrates that the Toshiba XG3 M.2 NVMe SSD is capable of, not only strong read IOPS at 214K, but write at 170K as well.  It is worthy of noting that, although the Samsung 950 Pro NVMe SSD has read IOPS just under 300K which betters the Toshiba considerably, the Toshiba XG3 has much better write IOPS where the Samsung couldn’t even reach 100K.

Toshiba XG3 1TB NVMe M.2 SSD AS SSD Copy Bench

The AS SSD Copy Benchmark tests the transfer of ISO, Program and Game files, recording the speed and time it takes to complete the transfer.  This test is as true to life as we will get from a synthetic benchmark and the Toshiba XG3 beat the Samsung 950 Pro hands down.  Samsung results can be found here.

ANVIL STORAGE UTILITIES PROFESSIONAL

Anvil’s Storage Utilities (ASU) are the most complete test bed available for the solid state drive today.  The benchmark displays test results for, not only throughput but also, IOPS and Disk Access Times.  Not only does it have a preset SSD benchmark, but also, it has included such things as endurance testing and threaded I/O read, write and mixed tests, all of which are very simple to understand and use in our benchmark testing.

Toshiba XG3 1TB NVMe M.2 SSD Anvil

Once again, we can see that test results are not always fluent between benchmark programs, Crystal DiskMark, AS SSD and ASU all testing with incompressible data samples.  Stay tuned as we get into PCMark 8 and some true data transfer testing.

PCMARK VANTAGE X64 HDD SUITE

The SSD Review uses benchmark software called PCMark Vantage x64 HDD Suite to create testing scenarios that might be used in the typical user experience. There are eight tests in all and the tests performed record the speed of data movement in MB/s to which they are then given a numerical score after all of the tests are complete.

PCMARK VANTAGE RESULTS

The Toshiba 1TB XG3 M.2 NVMe SSD achieved an excellent Total Score of 231552, again bettering the Samsung 950 Pro M.2 NVMe SSD.  All tests resulted in very high transfer speeds with 6 of the 8 tests achieving over 1GB/s.  The high speed goes to the Windows Startup test which achieved a transfer speed of 1.5GB/s.

Toshiba XG3 1TB NVMe M.2 SSD PCMark Vantage

19
Leave a Reply

avatar
9 Comment threads
10 Thread replies
0 Followers
 
Most reacted comment
Hottest comment thread
12 Comment authors
R. Rubbjp1wc1Douglas PayneNevin Sweigartdravo1 Recent comment authors
  Subscribe  
newest oldest most voted
Notify of
Benjamin Hojnik
Guest
Benjamin Hojnik

Thats some pretty good stuff from toshiba. And from 2D MLC flash.

I do wonder however what controller is that. Obviously its not made by toshiba. Something from OCZ maybe ? Or phison E7?

Les@TheSSDReview
Guest

There is a bit of investigation about the net that eludes to this being the Phison E-7, however, not enough to confirm or mention such within the article.

Shamoy Rahman
Guest
Shamoy Rahman

No, the controller is solely Toshiba’s.

Les@TheSSDReview
Guest

Link? Maybe a bit of validation or reasoning behind your thought?

Les@TheSSDReview
Guest

This is the Fujisan controller that was on display with OCZ as part of their Revo 400 release at Computex last year. We have elaborated on this within the report in controller description and the final para. This link shows what we posted prior.

http://www.thessdreview.com/daily-news/latest-buzz/ocz-prepares-new-revodrive-400-m-2-nvme-ssd-for-retail-release-computex-2015-update/

Benjamin Hojnik
Guest
Benjamin Hojnik

Thats some pretty good stuff from toshiba.

DarthDVD
Guest
DarthDVD

Bring on the 1Tb M.2 NVME Drives!!! (its the only thing stopping me from dropping a lot of moneys (and selling 1/2 a liver) and getting a new Rig.

Greg Zeng
Guest
Greg Zeng

Your claim for Crystal Disk Benchmark is several times higher than mine, on my 2013 Dell XPS-15 notebook computer. The original factory mSATA SSD was replaced a few months ago with a terabyte Samsung 850 EVO.

How comparable are the results of your tests, compared to those of your readers? If I install one of your tested products, how much performance difference should we expect? Several times?

My next upgrade might be to replace to original terabyte spinning HDD with a SSD of one or two terabytes. Perhaps.

DarthDVD
Guest
DarthDVD

The Samsung 850 EVO SSD (mSata) uses the mSata Standard and can not go as fast as the drives in this review.

The Drives in this review are M.2 (PCIE NVME) SSD’s and have access to 4 PCIE lanes which is Considerably much faster than Sata be it on: mSata on mini-pci(e) or M.2

https://en.wikipedia.org/wiki/M.2

Shamoy Rahman
Guest
Shamoy Rahman

You should’ve bought an M.2 or PCIE SSD if you wanted pure speed and didn’t care about the cost.

SkOrPn
Guest
SkOrPn

All I will say is you can’t really get away with comparing mSATA or SATA against PCIe storage. Its kinda like comparing PCIe video cards to AGP video cards, or even PCI to PCIe, it just isn’t a fair comparison. The PCIe bus is magnitudes better at moving data than the SATA bus will ever be. Now if you want to put FOUR 850 EVOs into RAID0, then we can talk comparisons because that MIGHT (I stress might, lol) compete with the single PCIe SSD given the usage scenario.

dzezik
Guest
dzezik

The advice to disable cache flush is wrong. You should only mark this option is the SSD has capacitors to protect unflushed data on power loss. So the drive runs faster but Your data is not safe, this is trade off. pease be aware of that. if the performance without this option is low then the controller or firmware is not well designed or… other controllers do not respect host request to flush cache. Do You have any information what is the real issue? Regards

Les@TheSSDReview
Guest

This is not uncommon. It is also much the same regardless of system and, yes is a tradeoff.

SSD QUICK SEARCH