Wow. They're not selling off the business, they're totally exiting it.
This is a big loss. Crucial offered a supply chain direct from Micron. Most other consumer DRAM sources pass through middlemen, where fake parts and re-labeled rejects can be inserted.
Should countries have a upper limit on the ratio of server:client memory supply chain capacity? If no one can buy client hardware to access the cloud, how would cloud providers survive after driving their customers to extinction?
It shouldn't be possible for one holding company (OpenAI) to silently buy all available memory wafer capacity from Samsung and SK Hynix, before the rest of civilization even has the opportunity to make a counteroffer.
I guess no Chinese interest wanted to buy it, to jumpstart a favored brand that's a step above random-name when people are picking which to buy on Amazon. Or wasn't willing to pay enough for it.
What a disaster for Micron. Having a consumer facing brand is 'crucial' for brand awareness. Micron is the smallest of the big 3 in DRAM and the only one in America. They're going to be swallowed up and replaced by CXMT.
The brand aware "consumers" are really just DIY PC builders, which is relatively a small number. Enterprise DRAM business is doing so great that Micron just doesn't see the consumer market is worth chasing.
This is bad for consumers though since DRAM prices are skyrocketing and now we have one less company making consumer DRAM.
The people who occupy the b2b ram buying kind of jobs are not aliens from another planet. Brand awareness in consumer markets, especially ones that are so closely tied to people's jobs (nerds gonna nerd) is going to have a knock on effect. It's not like a clothing brand or something.
You’re exactly wrong. In the race to supply AI data center, there is no “consumer” (in the sense I think you mean) making or influencing a buying decision. Without a clear path to increase supply, why take $1 when you can have $6 or $7?
Crucial was always a brand that I associated with quality, and I used their memory to upgrade several MacBooks back when it was still possible to upgrade the memory on MacBooks.
That being said, the only SSD I’ve ever had fail on me was from Crucial.
In recent builds I have been using less expensive memory from other companies with varying degrees of brand recognizability, and never had a problem. And the days of being able to easily swap memory modules seem numbered, anyway.
I also had a Crucial SSD fail. I believe it was either 256GB or 512GB SATA, around 2013-2014. Right around the same time OCZ released a batch of SSDs that were so bad they went out of business, despite being a leader in performance. It was a fairly large story about defective silicon. Good lesson in not being too loyal to brand names.
I don't know their breakdown for consumer vs enterprise, but the Crucial brand is consumer focussed. Obviously enterprise at this point is incredibly lucrative.
Sad. I've been buying Crucial as an attempt to avoid counterfeits, both buying direct and on eBay. Every DIMM and SSD from them has been perfect so far.
(ProTip: When you see 'Crucial'-labeled DIMMs with chips that don't have the Micron 'M' logo, I wouldn't buy that, or I would send it back.)
This seems a bit foolish? Even just limiting stock to paper launches and massively raising the price would let you say "oh, it's just the market" but here it makes them look like they're putting all their eggs in one basket.
I'm half joking but if this AI boom continues we're going to see Nvidia exit from consumer GPU business. But Jensen Huang will never do that to us... (I hope)
Why would anyone sell a handful of GPUs to nobodies like us when they could sell a million GPUs for thousands apiece to a handful of big companies? We're speedrunning the absolute worst corpo cyberpunk timeline.
They are already making moves that might suggest that future. They are going to stop packaging VRAM with their GPUs shipped to third-party graphics card makers, who will have to source their own, probably at higher cost.
Might almost be a good thing, if it means abandoning overhyped/underperforming high-end game rendering tech, and taking things in a different direction.
The push for 4K with raytracing hasn't been a good thing, as it's pushed hardware costs way up and led to the attempts to fake it with AI upscaling and 'fake frames'. And even before that, the increased reliance on temporal antialiasing was becoming problematic.
The last decade or so of hardware/tech advances haven't really improved the games.
Honestly, I'd prefer it. It might get AMD and Intel more off their ass for GPU development. I already stopped buying Nvidia gpus ages ago before they saw value in the Linux/Unix market, and I'm tired of them sucking up all the air in the room.
Their MX500 series SSDs were just king of price, performance and reliability. I even installed them in industrial PCs with intense vibrations and large temperature cycles, they're still chugging along like it's nothing.
Nearly every pc in my current collection has Crucial ram. My main desktop has a Crucial NVME drive, and I've got 2.5in SATA SSDs from Crucial in family computers.
I don't want to have to start buying obscure keysmash chinese brands for normal looking affordable hardware.
I have also bought Crucial for decades. Great quality and reliability for a fair price. Anybody doing anything semi-professional will be impacted by this questionable decision.
If you are going to sell shovels for a gold rush its pretty silly to keep rational market compatibility on things like prices, defect rate, packaging, correct contents.. Probably better to spare the brand (for a reboot?) and also not compete as much with all that junk when it shows up again on eBay.
Seems foolish, I've been a long-term shareholder in Micron but this seems aimed at short-term profit maximization. So I guess I'll be a short-term shareholder now.
> This decision reflects Micron’s commitment to its ongoing portfolio transformation and the resulting alignment of its business to secular, profitable growth vectors in memory and storage. By concentrating on core enterprise and commercial segments, Micron aims to improve long-term business performance and create value for strategic customers as well as stakeholders.
What the fuck does "secular" even mean in this context? Is there religious DRAM?
What a short-sighted, boneheaded move. I'm so tired of the MBA-ificiation of every single part of my life.
Yes, the MBAs and private equity firms are about 80% of the way through ruining everything that was ever good in the world. They've been accelerating exponentially. Probably won't be long now. I like to think it can't get much worse but I thought that several times before and I've been proven wrong each time. Optimism is getting much harder to hold on it.
Ah let my ask my new nerdy friend gemini3. Prompt: can you improve this text using plain english: This decision reflects Micron’s commitment to its ongoing portfolio transformation and the resulting alignment of its business to secular, profitable growth vectors in memory and storage. By concentrating on core enterprise and commercial segments, Micron aims to improve long-term business performance and create value for strategic customers as well as stakeholders.
Response (who said recently AI cannot do comedy):
Here are a few ways to rewrite this text using plain English, depending on how formal you want to be.
The original text relies heavily on corporate jargon like "secular growth vectors," "portfolio transformation," and "create value." The rewrites below aim to make these concepts concrete.
### Option 1: Professional & Direct (Best for reports or press)
> "Micron is shifting its strategy to focus on the most profitable, long-term growth areas in memory and storage. By targeting business and enterprise customers, the company aims to boost its long-term performance and deliver better results for customers and shareholders."
### Option 2: Concise (Best for quick updates)
> "Micron is refocusing on high-growth memory and storage markets to improve long-term profits. By concentrating on business customers rather than consumers, the company plans to create more value for its investors and clients."
### Option 3: Simple & Conversational (Best for spoken explanations)
> "This decision is part of Micron’s plan to change what we sell. We are focusing on business markets where we see steady, long-term growth. This will help us run a better business and help our customers and investors succeed."
---
### Key Changes Made
* *"Ongoing portfolio transformation"* Changed to *"shifting its strategy"* or *"changing what we sell."* This clarifies that the company is changing its mix of products.
* *"Secular... growth vectors"* Changed to *"long-term growth areas."* In finance, "secular" refers to trends that last a long time (as opposed to seasonal trends), but in plain English, it is often confusing.
* *"Core enterprise and commercial segments"* Changed to *"business and enterprise customers."* This clarifies who they are selling to.
*Would you like me to shorten this further for a slide deck or a specific headline?*
I consulted my paper dictionary, which doesn't use as much electricity as Belgium or thousands of gallons of water, and it reads: "of or relating to a long term of indefinite duration: <secular inflation>, <A secular increase in the quantity of money is required in a growing economy... – Milton Friedman>".
secular is the opposite of cyclical in business. ie a long-term trend.
And same. Though blowing significant fractions of a trillion dollars into (imo) investments that are never gonna return anything near to making that a good plan (ex a government bailout) will inevitably redirect huge portions of stuff we care about. The world's gdp is about 90T iirc; that is basically taking 1/90th of the stuff the world does in a year and putting it into ai.
When it eventually does, they'll just come up with something else. Nvidia got a taste of inflated prices from the Crypto and then AI, and they're not going to just let that go. If nothing exists they'll make something and hype it endlessly to try to keep this going.
> “The AI-driven growth in the data center has led to a surge in demand for memory and storage. Micron has made the difficult decision to exit the Crucial consumer business in order to improve supply and support for our larger, strategic customers in faster-growing segments,” said Sumit Sadana, EVP and Chief Business Officer at Micron Technology.
"AI"-driven collapse will go down as the stupidest crisis in human history. The idiotic waste of gigantic amounts of civilizatory resources, for something that hasn't remotely proven useful yet, while simultaneously neglecting existentially mandated reforms and investments, in an outrageously obvious critical moment in time ... well that's gonna dwarf even historic missteps of organized religion and island cultures.
I am calling it now:
* Cancelled: Cyberpunk.
* New lore timeline: Hypepunk > Crash-Core > Silicon Gothic
The term is up for grabs again. Also, future historians may not categorize medieval times as we do. By then, libraries may have been converted to data centers and historic artifacts burned to fuel GPUs, or destroyed through hallucinated restoration advice. Remaining digital traces may have been exhaustively overwritten by verbose AI prose, or simply lost when AWS introduced generative DNS. In a 1000 years, the only preserved evidence of medieval times may be an LLM's summary of "A Knight's Tale".
Dude, that's like someone's opinion. Also neural nets doing pattern recognition on x-ray images is not the reason Micron abandoned their consumer shovel business.
Even less consumer supply means higher prices. What’s fascinating is the very thing that enabled AI — gaming - may be one of the early casualties as it gains in priority.
Wow. They're not selling off the business, they're totally exiting it.
This is a big loss. Crucial offered a supply chain direct from Micron. Most other consumer DRAM sources pass through middlemen, where fake parts and re-labeled rejects can be inserted.
Should countries have a upper limit on the ratio of server:client memory supply chain capacity? If no one can buy client hardware to access the cloud, how would cloud providers survive after driving their customers to extinction?
It shouldn't be possible for one holding company (OpenAI) to silently buy all available memory wafer capacity from Samsung and SK Hynix, before the rest of civilization even has the opportunity to make a counteroffer.
We can prevent this from happening by enforcing 100-year-old antitrust laws.
Devices like smartphones and tablets that are locked down will continue to exist.
It’s these pesky pc things that people do bad things like piracy with/s
If you asked me to estimate the weighted fraction of clients accessing cloud services using devices with retail DIMMs, I would say much less than 1%.
It's not just retail DIMMS, most notebook and smartphone vendors are also impacted by NAND being redirected to datacenters.
It's the same memory wafer capacity. They're not separate.
Yeah but Micron is only exiting the retail business. They will still sell DIMMs to Dell, HP, Lenovo, etc.
They will probably sell Micron-label DIMMs to anyone who offers to buy 1000 of them.
I wonder why they didn't pull a GE, and sell/license the brand. But I'm glad they didn't.
Why would anybody buy it? This is a bad sign for consumer memory in general. It's more likely we're going to see more exits from this segment instead.
I guess no Chinese interest wanted to buy it, to jumpstart a favored brand that's a step above random-name when people are picking which to buy on Amazon. Or wasn't willing to pay enough for it.
There is KLEVV, the outlet of SK Hynix. They are crass!
https://www.klevv.com/ken/main
And don't forget about https://www.nanya.com/en/
While I never had a problem with https://semiconductor.samsung.com/dram/module/ , I think they will be rare/more expensive now, or 'soonish'.
For chinese CXMT and YMTC there is https://www.biwintech.com/
We live in interesting times!
(Cackling madly...)
What a disaster for Micron. Having a consumer facing brand is 'crucial' for brand awareness. Micron is the smallest of the big 3 in DRAM and the only one in America. They're going to be swallowed up and replaced by CXMT.
The brand aware "consumers" are really just DIY PC builders, which is relatively a small number. Enterprise DRAM business is doing so great that Micron just doesn't see the consumer market is worth chasing.
This is bad for consumers though since DRAM prices are skyrocketing and now we have one less company making consumer DRAM.
The people who occupy the b2b ram buying kind of jobs are not aliens from another planet. Brand awareness in consumer markets, especially ones that are so closely tied to people's jobs (nerds gonna nerd) is going to have a knock on effect. It's not like a clothing brand or something.
https://www.biwintech.com/
You’re exactly wrong. In the race to supply AI data center, there is no “consumer” (in the sense I think you mean) making or influencing a buying decision. Without a clear path to increase supply, why take $1 when you can have $6 or $7?
Crucial was always a brand that I associated with quality, and I used their memory to upgrade several MacBooks back when it was still possible to upgrade the memory on MacBooks.
That being said, the only SSD I’ve ever had fail on me was from Crucial.
In recent builds I have been using less expensive memory from other companies with varying degrees of brand recognizability, and never had a problem. And the days of being able to easily swap memory modules seem numbered, anyway.
I also had a Crucial SSD fail. I believe it was either 256GB or 512GB SATA, around 2013-2014. Right around the same time OCZ released a batch of SSDs that were so bad they went out of business, despite being a leader in performance. It was a fairly large story about defective silicon. Good lesson in not being too loyal to brand names.
This will surely maximize quarterly profits until the next cloud or AI bust.
Diversification is resilience.
Putting consumer on hold makes some sense. An exit? This will be written about in business books.
Micron are estimated to have 23% and 21% of global revenue for DRAM and HBM in Q2 2025.
Their 'smaller' market, SSDs - has an estimated 13% of global NAND revenue.
https://counterpointresearch.com/en/insights/global-dram-and... https://counterpointresearch.com/en/insights/global-nand-mem...
I don't know their breakdown for consumer vs enterprise, but the Crucial brand is consumer focussed. Obviously enterprise at this point is incredibly lucrative.
We're gonna need a bigger pin.
Tangent: this is going to happen with SOTA LLMs as well, isn't it.
Consumers are so annoying. And by consumers, I mean "anyone can get an API key for the latest model."
Sad. I've been buying Crucial as an attempt to avoid counterfeits, both buying direct and on eBay. Every DIMM and SSD from them has been perfect so far.
(ProTip: When you see 'Crucial'-labeled DIMMs with chips that don't have the Micron 'M' logo, I wouldn't buy that, or I would send it back.)
This seems a bit foolish? Even just limiting stock to paper launches and massively raising the price would let you say "oh, it's just the market" but here it makes them look like they're putting all their eggs in one basket.
Uh shite. That's the goto for ssds with capacitors on, such that when the power dies they're able to leave things in a reasonable state.
All the samsung ones I've tried have died within a year. Fast until they died I suppose.
Any recommendations for nvme in a post-micron world?
MBA/Wall Street short term driven decision.
I'm half joking but if this AI boom continues we're going to see Nvidia exit from consumer GPU business. But Jensen Huang will never do that to us... (I hope)
Why would anyone sell a handful of GPUs to nobodies like us when they could sell a million GPUs for thousands apiece to a handful of big companies? We're speedrunning the absolute worst corpo cyberpunk timeline.
There is a couple reasons why Jensen won't take off the gaming leather jacket just yet:
1. Gaming cards are their R&D pipeline for data center cards. Lots of innovation came from gaming cards.
2. Its a market defense to keep other players down and keep them from growing their way into data centers.
3. Its profitable (probably the main reason but boring)
4. Hedge against data center volatility (10 key customers vs millions)
5. Antitrust defense (which they used when they tried to buy ARM)
6. Techies who use NVidia GPUs in their PCs are more likely to play with AI and ultimately contributing to the space as either a developer or a user
They are already making moves that might suggest that future. They are going to stop packaging VRAM with their GPUs shipped to third-party graphics card makers, who will have to source their own, probably at higher cost.
Might almost be a good thing, if it means abandoning overhyped/underperforming high-end game rendering tech, and taking things in a different direction.
The push for 4K with raytracing hasn't been a good thing, as it's pushed hardware costs way up and led to the attempts to fake it with AI upscaling and 'fake frames'. And even before that, the increased reliance on temporal antialiasing was becoming problematic.
The last decade or so of hardware/tech advances haven't really improved the games.
The way things are going no one will be able to afford a PC.
Instead we will be streaming games from our locked down tablets and paying a monthly subscription for the pleasure.
You will own nothing and be happy.
I think Nvidia realises that selling GPUs to individuals is useful as it allows them to develop locally with CUDA.
Honestly, I'd prefer it. It might get AMD and Intel more off their ass for GPU development. I already stopped buying Nvidia gpus ages ago before they saw value in the Linux/Unix market, and I'm tired of them sucking up all the air in the room.
Their MX500 series SSDs were just king of price, performance and reliability. I even installed them in industrial PCs with intense vibrations and large temperature cycles, they're still chugging along like it's nothing.
Just bought one last week, sadly not many options left for 2.5" SSDs
Nearly every pc in my current collection has Crucial ram. My main desktop has a Crucial NVME drive, and I've got 2.5in SATA SSDs from Crucial in family computers.
I don't want to have to start buying obscure keysmash chinese brands for normal looking affordable hardware.
God dammit Micron.
I have also bought Crucial for decades. Great quality and reliability for a fair price. Anybody doing anything semi-professional will be impacted by this questionable decision.
If you are going to sell shovels for a gold rush its pretty silly to keep rational market compatibility on things like prices, defect rate, packaging, correct contents.. Probably better to spare the brand (for a reboot?) and also not compete as much with all that junk when it shows up again on eBay.
(Crucial the brand not the adjective)
They announced a month ago that their upstate NY fab was delayed by 2-3 years so the painting was on the wall
https://archive.md/WSsLm
https://www.syracuse.com/micron/2025/11/micron-chip-factorie...
They don't need the fab for Crucial the brand.
Anything the fab outputs will feed into Micron selling to datacenters
Seems foolish, I've been a long-term shareholder in Micron but this seems aimed at short-term profit maximization. So I guess I'll be a short-term shareholder now.
> This decision reflects Micron’s commitment to its ongoing portfolio transformation and the resulting alignment of its business to secular, profitable growth vectors in memory and storage. By concentrating on core enterprise and commercial segments, Micron aims to improve long-term business performance and create value for strategic customers as well as stakeholders.
What the fuck does "secular" even mean in this context? Is there religious DRAM?
What a short-sighted, boneheaded move. I'm so tired of the MBA-ificiation of every single part of my life.
Yes, the MBAs and private equity firms are about 80% of the way through ruining everything that was ever good in the world. They've been accelerating exponentially. Probably won't be long now. I like to think it can't get much worse but I thought that several times before and I've been proven wrong each time. Optimism is getting much harder to hold on it.
Ah let my ask my new nerdy friend gemini3. Prompt: can you improve this text using plain english: This decision reflects Micron’s commitment to its ongoing portfolio transformation and the resulting alignment of its business to secular, profitable growth vectors in memory and storage. By concentrating on core enterprise and commercial segments, Micron aims to improve long-term business performance and create value for strategic customers as well as stakeholders.
Response (who said recently AI cannot do comedy):
Here are a few ways to rewrite this text using plain English, depending on how formal you want to be.
The original text relies heavily on corporate jargon like "secular growth vectors," "portfolio transformation," and "create value." The rewrites below aim to make these concepts concrete.
### Option 1: Professional & Direct (Best for reports or press) > "Micron is shifting its strategy to focus on the most profitable, long-term growth areas in memory and storage. By targeting business and enterprise customers, the company aims to boost its long-term performance and deliver better results for customers and shareholders."
### Option 2: Concise (Best for quick updates) > "Micron is refocusing on high-growth memory and storage markets to improve long-term profits. By concentrating on business customers rather than consumers, the company plans to create more value for its investors and clients."
### Option 3: Simple & Conversational (Best for spoken explanations) > "This decision is part of Micron’s plan to change what we sell. We are focusing on business markets where we see steady, long-term growth. This will help us run a better business and help our customers and investors succeed."
---
### Key Changes Made
* *"Ongoing portfolio transformation"* Changed to *"shifting its strategy"* or *"changing what we sell."* This clarifies that the company is changing its mix of products. * *"Secular... growth vectors"* Changed to *"long-term growth areas."* In finance, "secular" refers to trends that last a long time (as opposed to seasonal trends), but in plain English, it is often confusing. * *"Core enterprise and commercial segments"* Changed to *"business and enterprise customers."* This clarifies who they are selling to.
*Would you like me to shorten this further for a slide deck or a specific headline?*
I consulted my paper dictionary, which doesn't use as much electricity as Belgium or thousands of gallons of water, and it reads: "of or relating to a long term of indefinite duration: <secular inflation>, <A secular increase in the quantity of money is required in a growing economy... – Milton Friedman>".
https://en.wiktionary.org/wiki/secular
>Is there religious DRAM?
RAM optimized for TempleOS and Holy-C
secular is the opposite of cyclical in business. ie a long-term trend.
And same. Though blowing significant fractions of a trillion dollars into (imo) investments that are never gonna return anything near to making that a good plan (ex a government bailout) will inevitably redirect huge portions of stuff we care about. The world's gdp is about 90T iirc; that is basically taking 1/90th of the stuff the world does in a year and putting it into ai.
I’m sure that decision will look real smart in 3 years time.
Can tell if sarcastic.
I hate everything about this. Nothing good is coming from this AI hype bubble.
That's a shame. I liked buying RAM from them.
Micron leadership probably just heard about Roko's basilisk.
Insane decision. This whole bubble is irrational.
I've only ever bought crucial ram for the past 20 years.
When richer people than you want things, those things can become unavailable to you (or at least less available).
I really hope this bubble pops, all these investors lose their shirts, and prices come down to something reasonable.
When it eventually does, they'll just come up with something else. Nvidia got a taste of inflated prices from the Crypto and then AI, and they're not going to just let that go. If nothing exists they'll make something and hype it endlessly to try to keep this going.
Then I sure hope Nvidia completely ceases to exist, like SGI, who, ironically, was decimated by Nvidia and cheap consumer hardware.
> “The AI-driven growth in the data center has led to a surge in demand for memory and storage. Micron has made the difficult decision to exit the Crucial consumer business in order to improve supply and support for our larger, strategic customers in faster-growing segments,” said Sumit Sadana, EVP and Chief Business Officer at Micron Technology.
"AI"-driven collapse will go down as the stupidest crisis in human history. The idiotic waste of gigantic amounts of civilizatory resources, for something that hasn't remotely proven useful yet, while simultaneously neglecting existentially mandated reforms and investments, in an outrageously obvious critical moment in time ... well that's gonna dwarf even historic missteps of organized religion and island cultures.
I am calling it now:
* Cancelled: Cyberpunk.
* New lore timeline: Hypepunk > Crash-Core > Silicon Gothic
* Historian epoch title: The Dark Ages.
Indeed it was naive of us not to have called that controversial medieval lull in societal progress "The First Dark Ages".
https://en.wikipedia.org/wiki/Dark_Ages_(historiography)
The term is up for grabs again. Also, future historians may not categorize medieval times as we do. By then, libraries may have been converted to data centers and historic artifacts burned to fuel GPUs, or destroyed through hallucinated restoration advice. Remaining digital traces may have been exhaustively overwritten by verbose AI prose, or simply lost when AWS introduced generative DNS. In a 1000 years, the only preserved evidence of medieval times may be an LLM's summary of "A Knight's Tale".
"The idiotic waste of gigantic amounts of civilizatory resources, for something that hasn't remotely proven useful yet"
https://ai.nejm.org/doi/full/10.1056/AI-S2501208
Remember when AOL bought Time Warner?
I do think it's proven useful, much like the internet had in the nineties.
Dude, that's like someone's opinion. Also neural nets doing pattern recognition on x-ray images is not the reason Micron abandoned their consumer shovel business.
Even less consumer supply means higher prices. What’s fascinating is the very thing that enabled AI — gaming - may be one of the early casualties as it gains in priority.
Another Big Tech company getting hollowed out to maximize short term profits.
This brand has existed for what, 20+ years? You dont think they can look at long-term trendlines of revenue and expenses?
Please explain how this is "short term" thinking.
This is very sad. Ive been using Crucial for decades, the most reliable I have ever had.