Skip to main content

Intel Optane memory: Everything you need to know

Intel Optane makes old hard drives as fast as modern SSDs

Image used with permission by copyright holder

Intel Optane memory might sound like a new standard of RAM, but it has more in common with modern storage solutions like solid state drives (SSDs). Yet it’s designed to supplant SSDs in some ways — and augment them in others. In short, Intel Optane provides much faster read and write speeds than even the fastest SSD can match without RAM’s constant power requirement.

Recommended Videos

More than a year on from the technology’s debut though, it hasn’t been quite as impactful as some might have expected. Some of that surely has to do with some confusion as to what exactly Intel Optane does and where you can find it — so let’s clear some things up.

Where can you find it?

Today there are a number of Intel Optane-equipped SSDs available. The first to appear was Intel’s DC 4800X SSD. That name isn’t catchy, because it doesn’t have to be. It’s an enterprise product, where potential buyers are far more concerned with dollars per performance than branding or aesthetics.

There are more options for the average person, too. Intel launched 60GB and 120GB Optane SSDs earlier this year, priced at $130 and $200 respectively. Using Intel’s 3D XPoint memory modules, they offered high-speed read and write rates that rival strong M.2 and NVMe SSDs from more traditional SSD manufacturers, but only in small capacities. Their small form-factor makes them viable options for inclusion in miniature PC builds and laptops, though their higher-than-average cost per gigabyte still makes them uncommon in pre-built systems.

Intel followed up that launch with the much more performance-focused Intel Optane 900P and 905P range of SSDs later in the year and eventually expanded size options for the latter range in September. Today the PCIe Optane SSDs are available in 500GB, 1TB, and 1.5TB sizes, with the 905P range offering sequential read and write speeds as high as 2,600MB/sec and 2,200MB/sec.

Intel Optane review
Image used with permission by copyright holder

At the other end of the spectrum, Intel Optane Memory attempts something much more like the enterprise-focused DC 4800X. The 16GB and 32GB devices are designed to act like caching drives, automatically keeping the most commonly used files on that drive, giving old HDDs a boost of speed. We spent some time with those drives, and though enthusiasts will want to opt for dedicated SSDs, systems like the Acer Aspire 5 really benefited from the fast caching abilities of Optane memory. Even impressive all-in-one systems like the HP Envy 27 have taken advantage of it.

The big reason manufacturers (and hence, the average person) can benefit from Optane is cost. A 16GB Optane module costs just $34 to consumers — and likely far less when purchased in bulk by system builders. That’s far cheaper than trying to pack in a middling-size SSD that only offers greater performance up to its own capacity. An Optane module can boost a far greater amount of data than its modest size might suggest, switching out what it stores to whatever is accessed most often.

Under the hood

So, what exactly is Intel Optane? We aren’t quite sure, because Intel won’t tell us. The company has even responded to questions of the underlying materials with cagey answers and “no comments,” which leaves us wondering what sort of digital witchcraft powers this fast, non-volatile storage.

What we do know is rather basic. Optane is based on a previously announced Intel and Micron project knows as 3D XPoint, and the details quickly grow complex from there. In essence, it allows for greater speeds by changing the resistance across bits in large batches, rather than one at a time, and packs in more of that memory by stacking the arrays in rows, which are turned 90 degrees on each layer. The image below lays out an example of how this looks at a microscopic level.

Image used with permission by copyright holder

Don’t confuse 3D XPoint with 3D NAND, however, which is simply flash memory stacked in more efficient configurations. Instead, 3D XPoint operates on (possibly) different materials, with proprietary forms of data storage and transfer, the details of which are a closely guarded secret.

It also isn’t the end of the story, because 3D XPoint is just the storage type, while Optane is a collection of first-party Intel hardware, firmware, and software that turns that mysterious chunk of whatever-it-is into a device that’s usable in a myriad of situations. Intel has quickly expanded its range of Intel Optane products from some simple caching hardware, to dedicated storage drives which are getting bigger and more affordable all the time.

Jon Martindale
Jon Martindale is a freelance evergreen writer and occasional section coordinator, covering how to guides, best-of lists, and…
Topics
DeepSeek: everything you need to know about the AI that dethroned ChatGPT
robot hand in point space

A year-old startup out of China is taking the AI industry by storm after releasing a chatbot which rivals the performance of ChatGPT while using a fraction of the power, cooling, and training expense of what OpenAI, Google, and Anthropic's systems demand. Here's everything you need to know about Deepseek's V3 and R1 models and why the company could fundamentally upend America's AI ambitions.
What is DeepSeek?
DeepSeek (technically, "Hangzhou DeepSeek Artificial Intelligence Basic Technology Research Co., Ltd.") is a Chinese AI startup that was originally founded as an AI lab for its parent company, High-Flyer, in April, 2023. That May, DeepSeek was spun off into its own company (with High-Flyer remaining on as an investor) and also released its DeepSeek-V2 model. V2 offered performance on par with other leading Chinese AI firms, such as ByteDance, Tencent, and Baidu, but at a much lower operating cost.

The company followed up with the release of V3 in December 2024. V3 is a 671 billion-parameter model that reportedly took less than 2 months to train. What's more, according to a recent analysis from Jeffries, DeepSeek's “training cost of only US$5.6m (assuming $2/H800 hour rental cost). That is less than 10% of the cost of Meta’s Llama.” That's a tiny fraction of the hundreds of millions to billions of dollars that US firms like Google, Microsoft, xAI, and OpenAI have spent training their models.

Read more
Everything you need to know about AI agents and what they can do
a hollow man under light

The agentic era of artificial intelligence has arrived. AI agents are capable of operating independently and without continuous, direct oversight, while collaborating with users to automate monotonous tasks. Based on the same large language models that drive popular chatbots like ChatGPT and Google Gemini, agentic AIs differ in that they use LLMs to take action on a user's behalf rather than generate content.

In this guide, you'll find everything you need to know about how AI agents are designed, what they can do, what they're capable of, and whether they can be trusted to act on your behalf.
What is an agentic AI?
Billed as "the next big thing in AI research," agentic AI is a type of generative AI model that can act autonomously, make decisions, and take actions towards complex goals without direct human intervention. These systems are able to interpret changing conditions in real-time and react accordingly, rather than rotely following predefined rules or instructions.

Read more
AMD calls Intel’s Arrow Lake ‘horrible’
Fingers holding an Intel 285K.

Shots fired. Frank Azor, an AMD executive, just straight-up called Intel's Arrow Lake line of CPUs "horrible." Where did it all start? Why, with the ongoing shortage of AMD’s best gaming processors, of course. And surprisingly, AMD blames Intel for the fact that its X3D processors are hard to come by right now.

In a recent media roundtable reported by Tom's Hardware, AMD admitted that it never expected the demand for its CPUs to be that high. In fact, it expected it to be lower because it thought that Intel would be more competitive -- but since Arrow Lake turned out to be largely unimpressive, people turned to AMD for their next-gen CPUs even more so than before.

Read more