Semiwiki on LinkedIn Semiwiki on Facebook Semiwiki on Twitter Register / Log in 
Array
(
    [content] => 
    [params] => Array
        (
            [0] => /forum/threads/intel-expected-to-begin-shipping-apple%E2%80%99s-lowest-end-m-processor-as-early-as-2027.24104/
        )

    [addOns] => Array
        (
            [DL6/MLTP] => 13
            [Hampel/TimeZoneDebug] => 1000070
            [SV/ChangePostDate] => 2010200
            [SemiWiki/Newsletter] => 1000010
            [SemiWiki/WPMenu] => 1000010
            [SemiWiki/XPressExtend] => 1000010
            [ThemeHouse/XLink] => 1000970
            [ThemeHouse/XPress] => 1010570
            [XF] => 2030770
            [XFI] => 1060170
        )

    [wordpress] => /var/www/html
)

Intel expected to begin shipping Apple’s lowest-end M processor as early as 2027

S

siliconbruh999

Well-known member
Intel expected to begin shipping Apple’s lowest-end M processor as early as 2027

There have long been market rumors that Intel could become an advanced-node foundry supplier to Apple, but visibility around this had remained low. My latest industry surveys, however, indicate that visibility on Intel becoming an advanced-node supplier to Apple has recently improved significantly.

Apple previously signed an NDA with Intel and obtained the advanced-node 18AP PDK 0.9.1GA. The key simulation and research projects (such as PPA) are tracking in line with expectations, and Apple is now waiting for Intel to release PDK 1.0/1.1, currently scheduled for 1Q26. Apple's plan is for Intel to begin shipping its lowest-end M processor, utilizing the 18AP advanced node, as early as 2Q–3Q27, but the actual timeline remains contingent on development progress following the receipt of PDK 1.0/1.1.

Apple’s lowest-end M processor is currently used in the MacBook Air and iPad Pro mainly, with combined shipments of roughly 20 million units for 2025. As MacBook Air shipments in 2026 may be impacted by a new more-affordable MacBook model using an iPhone-class processor, shipments of lowest-end M processor in both 2026 and 2027 are expected to be 15–20 million units.

In absolute terms, order volumes for the lowest-end M processor are relatively small and virtually no material impact on TSMC’s fundamentals or its technology leadership over the next several years. However, the signaling and trend implications for Apple and Intel are meaningful:

1. For Apple: In addition to showing strong support for the Trump administration’s strongly promoted “Made in USA” policy, Apple, while clearly expected to remain highly dependent on TSMC’s advanced nodes for the foreseeable future, still needs to secure a second source to meet supply-chain management requirements.

2. For Intel: The significance of winning Apple’s advanced-node orders far exceeds the direct revenue and profit contribution from this business. Although Intel will still be unable to compete head-to-head with TSMC over the next several years, this suggests that the worst may soon be over for the IFS business. Looking ahead, the 14A node and beyond could capture more orders from Apple and other tier-one customers, turning Intel’s long-term outlook more positive.

https://twitter.com/x/status/1994422001952555318
 
IMG_1709.jpeg


Napkin math:
Given M4’s ~160mm2 size and just defaults for yield on semi analysis’s tool we get 318 good dies per wafer.

If Intel were to (miraculously) capture all M7 market at ~20M products a year, then that’s 63,000 wafers a year, or ~5,200 WSPM.

A nice start for a foundry, but really not much…
 
siliconbruh999 said:
Intel expected to begin shipping Apple’s lowest-end M processor as early as 2027

There have long been market rumors that Intel could become an advanced-node foundry supplier to Apple, but visibility around this had remained low. My latest industry surveys, however, indicate that visibility on Intel becoming an advanced-node supplier to Apple has recently improved significantly.
Click to expand...

Great Info. Intel needs to start small and no one would commit major line to Intel.

Couple notes:
Assuming Intel gets some customers, They will not break even in 2027 UNLESS they take a major write off before (obviously anyone can break even by writing everything off earlier)

Intels challenge is that it is not cost effective due to scale and unmanufacturable processes. If Intel ramped 1 whole 18A fab on an external customer today, their losses would increase, not decrease.

Monitor the low volume plans and delivery, Monitor margins going forward. these are the challenges AFTER they finally win customers.
 
MKWVentures said:
Great Info. Intel needs to start small and no one would commit major line to Intel.

Couple notes:
Assuming Intel gets some customers, They will not break even in 2027 UNLESS they take a major write off before (obviously anyone can break even by writing everything off earlier)

Intels challenge is that it is not cost effective due to scale and unmanufacturable processes. If Intel ramped 1 whole 18A fab on an external customer today, their losses would increase, not decrease.

Monitor the low volume plans and delivery, Monitor margins going forward. these are the challenges AFTER they finally win customers.
Click to expand...
I guess that’s a good excuse for not breaking even, as making IFS viable could be beneficial to the valuation. I remember DZ saying on multiple occasions that a properly run fab company should be valued at 1–2× its book value.

Should we focus on future cash flows instead of break-even timing?
 
If true, it's probably a diversification/margins play for Apple. I would imagine that at this moment AI players (NVIDIA, AMD, Alphabet) might be willing to pay TSMC more for the silicon than Apple. Still, again - if true, it will be seen as a stamp of approval for IFS from an important customer.
 
lilo777 said:
If true, it's probably a diversification/margins play for Apple. I would imagine that at this moment AI players (NVIDIA, AMD, Alphabet) might be willing to pay TSMC more for the silicon than Apple. Still, again - if true, it will be seen as a stamp of approval for IFS from an important customer.
Click to expand...
Maybe there is some truth to those Apple 14a rumors!
 
MKWVentures said:
Great Info. Intel needs to start small and no one would commit major line to Intel.

Couple notes:
Assuming Intel gets some customers, They will not break even in 2027 UNLESS they take a major write off before (obviously anyone can break even by writing everything off earlier)

Intels challenge is that it is not cost effective due to scale and unmanufacturable processes. If Intel ramped 1 whole 18A fab on an external customer today, their losses would increase, not decrease.

Monitor the low volume plans and delivery, Monitor margins going forward. these are the challenges AFTER they finally win customers.
Click to expand...

A recent development may significantly affect when Intel can return to profitability: the alleged IP theft committed by Mr. Wei-Jen Lo, a former TSMC executive who now works for Intel.

Regardless of the outcomes of the civil and criminal cases against Mr. Wei-Jen Lo, TSMC has many direct and indirect ways to let Intel know the consequences of losing trust in the relationship between the two companies.
 
There are reports in Taiwan suggesting that TSM is worried about being targeted for antitrust action, as many agree that it monopolises the market for advanced processes. In my opinion, Intel should explore this angle, as imposing harsh hurdles on employee mobility is anti-competitive. For a similar reason, companies in California cannot enforce non-compete restrictions.

From LBT's recent remark:
“Freedom to work, to apply our skills, and to move between companies has been a cornerstone of innovation in the semiconductor industry since the earliest days."
 
Last edited:
ChatGPT:

Query: Why does California do not enforce non-compete?

Reply:

California’s refusal to enforce non-compete agreements comes from a long-standing legal and economic philosophy that prioritises innovation, competition, and employee mobility. The reasons are structural, not incidental.


Here are the core reasons:



✅ 1.​


The key statute is:


California Business & Professions Code §16600


“Every contract by which anyone is restrained from engaging in a lawful profession, trade, or business of any kind is to that extent void.”
Click to expand...

This has been the law since 1872.
So unlike other states where courts interpret reasonableness, California outright bans them.



✅ 2.​


California—especially Silicon Valley—believes that:


  • Innovation thrives when people can switch companies easily
  • Talent flows create new startups and competition
  • Knowledge spillover accelerates technological progress

This belief was reinforced by historical observation:
Silicon Valley grew faster than Boston’s Route 128 partly because employee mobility was more fluid.



✅ 3.​


California courts and lawmakers view non-competes as:


  • Restricting market freedom
  • Locking talent inside incumbents
  • Preventing new companies from forming
  • Reducing competition in the labour market

This aligns with modern economic research and the recent 2024 FTC decision to ban most non-competes nationwide.



✅ 4.​


Historically, California has:


  • Favoured workers’ rights
  • Encouraged job mobility and entrepreneurship
  • Reduced ability of large employers to control ex-employees

This is part of the state’s broader pro-worker legal tradition.



✅ 5.​


Silicon Valley culture emphasises:


  • Rapid iteration
  • Talent movement
  • Startups formed by people leaving big incumbents
  • Cross-pollination of ideas

Non-competes would have slowed or prevented landmark companies like Google, Facebook, Nvidia, Tesla, etc.



⭐ Summary​


California does not enforce non-competes because:


  1. State law specifically bans them (§16600).
  2. They believe mobility drives innovation and economic growth.
  3. Non-competes are seen as anti-competitive.
  4. The legal tradition favours workers and startups.
  5. They fit the tech ecosystem’s culture.


If you'd like, I can also compare California’s approach with Taiwan, Australia, or other U.S. states.
 
XYang2023 said:
There are reports in Taiwan suggesting that TSM is worried about being targeted for antitrust action, as many agree that it monopolises the market for advanced processes. In my opinion, Intel should explore this angle, as imposing harsh hurdles on employee mobility is anti-competitive. For a similar reason, companies in California cannot enforce non-compete restrictions.

From LBT's recent remark:
“Freedom to work, to apply our skills, and to move between companies has been a cornerstone of innovation in the semiconductor industry since the earliest days."
Click to expand...
Who exactly is "imposing harsh hurdles on employment mobility" and how ?


It's also interesting to note historically that Intel were particularly intolerant of defectors. While being founded by defectors from other companies, Andy Grove and co apparently didn't take it well when people left Intel to do the same as he did.
 
tooLongInEDA said:
Who exactly is "imposing harsh hurdles on employment mobility" and how ?


It's also interesting to note historically that Intel were particularly intolerant of defectors. While being founded by defectors from other companies, Andy Grove and co apparently didn't take it well when people left Intel to do the same as he did.
Click to expand...
Well, at least Intel did not sue WJL when he left Intel for TSMC. Also, I believe Intel has (or, at least, had) a policy that those, who left the company but decided to come back within 3 months, get fully restored in their seniority and related benefits.
 
The public stunt carried out with the help of the Taiwanese government—raiding his home and seizing his shares—is not only directed at WJL but also serves as a serious warning to any current employees who might be considering a move to Intel. I think that’s quite harsh, and TSM should have handled the situation differently.

When I posted my message, I also asked GPT to review it:

1764406946732.png
 
"I can assure you Lip-Bu is talking to Apple. He did the keynote at the GSA US Executive Forum last night in Menlo Park pumping Intel's importance and the road to $1T valuation by 2030. His candor and vision was greatly appreciated."

B

Thread 'Bloomberg: Intel Is Seeking an Investment From Apple as Part of Its Comeback Bid'

Ryan Gould and Liana Baker
Wed, September 24, 2025 at 4:16 PM CDT 4 min read

(Bloomberg) -- Intel Corp. has approached Apple Inc. about securing an investment in the ailing chipmaker, according to people familiar with the matter, part of efforts to bolster a business that’s now partially owned by the US government.

Apple and Intel also have discussed how to work more closely together, said the people, who asked not to be identified because the deliberations are private. The talks have been early-stage and may not lead to an agreement, the people said.

1758762897631.png

Intel CEO Lip-Bu Tan has...
 
Daniel Nenni said:
"I can assure you Lip-Bu is talking to Apple. He did the keynote at the GSA US Executive Forum last night in Menlo Park pumping Intel's importance and the road to $1T valuation by 2030. His candor and vision was greatly appreciated."

B

Thread 'Bloomberg: Intel Is Seeking an Investment From Apple as Part of Its Comeback Bid'

Ryan Gould and Liana Baker
Wed, September 24, 2025 at 4:16 PM CDT 4 min read

(Bloomberg) -- Intel Corp. has approached Apple Inc. about securing an investment in the ailing chipmaker, according to people familiar with the matter, part of efforts to bolster a business that’s now partially owned by the US government.

Apple and Intel also have discussed how to work more closely together, said the people, who asked not to be identified because the deliberations are private. The talks have been early-stage and may not lead to an agreement, the people said.

1758762897631.png

Intel CEO Lip-Bu Tan has...
Click to expand...
Did you hear him say that - "$1T valuation by 2030" in person?
 
You must log in or register to reply here.
Back
Top