[aurareturn]

A hypothetical M7 Ultra with LPDDR6 14.4Gbps memory would be 1.85 Tb/s.

You're look at about 100 tokens/s for a 1T MoE 37B active 4bit model.

It'd probably cost $30k or more I'm guessing if memory prices do not come down. Even at $30k, it could still be a relative bargain since an RTX Pro 6000 Blackwell 96GB card costs $12k today. The M3 Ultra with 512GB was around $8k before Apple discontinued it. I expect an M7 Ultra to have 768GB or 1024GB.

Apple Silicon Macs were on their way to becoming cheap local LLM machines relative to professional GPUs before this memory crisis. It may still emerge as such in a few years.

Here's some interesting math: At 512GB, an Ultra chip could make 42 pro iPhones. Assume a 55% profit margins, and $1200 ASP, you're looking at $28,160 in profit from making iPhones instead. No wonder Apple discontinued the M3 Ultra 512GB. If they only have a limited supply of RAM for all their products, it makes no sense to produce an $8000 M3 Ultra 512GB when you can produce 42 pro iPhones. You can only configure an M3 Ultra up to 96GB today as of June 2026.

Apple would have to raise the price of a 512GB Ultra Mac to around $50k to match iPhone profits.

[benoau]

> Assume a 55% profit margins, and $1200 ASP, you're looking at $28,160 in profit from making iPhones instead. No wonder Apple discontinued the M3 Ultra 512GB.

How would that work? They purchase 512GB from Samsung and then it doesn't matter if that's like 128x 4GB or 4x 128GB?

[Schiendelman]

It's likely the capacity they have reserved can be in different combinations.

[bel8]

Note that this reserved capacity now has competition from OpenAI, Anthropic, xAI, Meta, Microsoft, Chinese data centers and so on, all willing to pay premium.

If comapnies keep spending half a macbook neo worth of subscription on AI plans monthly per person, Apple is going to have a hard time competing.

[mcintyre1994]

Companies are spending even more than that if they’re using the $200 subscription worth of tokens on the enterprise plans too.

[airstrike]

That's a very big if, though. There's been extensive news coverage about companies increasingly trying to move away from tokenmaxxing

[nok22kon]

but they move from tokenmaxxing to tokenmidding, not to tokenzero

[jurgenburgen]

> A hypothetical M7 Ultra with LPDDR6

That’s indeed very hypothetical considering that Apple silicon uses on-package HBM.

[throw1234567891]

> The M3 Ultra with 512GB was around $8k before Apple discontinued it

The base model was $9k, that much RAM got you into $14k range.

[brookst]

Where did you get 55% from? iPhone and Mac gross margins behave been 40% or so for years IIRC.

[aurareturn]

Quick internet search. Whether it’s 40% or 55%, the main points stay.

[NuclearPM]

An ‘ypothetical!

[zombot]

In what neck of the woods? English pronunciation never gets boring.

[swiftcoder]

In British English the "an" is correct, even though most English dialects don't actually render the H as silent. It's a French-derived word that had a silent H originally, ergo we use "an".

[ls612]

I’d assume by next year the open weights models will be outlawed the way things are going nowadays :/

Edit: for those of you downvoting I don’t celebrate this prospect. I’m merely realistic about where things are going given the rapid vibe shift from the administration on AI since the start of June.